Social media platform has greatly enhanced human interactive activities in the virtual community. Virtual
socialization has positively influenced social bonding among social media users irrespective of one’s
location in the connected global village. Human user and social bot user are the two types of social media
users. While human users personally operate their social media accounts, social bot users are developed
software that manages a social media account for the human user called the botmaster. This botmaster in
most cases are hackers with bad intention of attacking social media users through various attacking mode
using social bots. The aim of this research work is to design an intelligent framework that will prevent
attacks through social bots on social media network platforms.
Exploratory Data Analysis and Feature Selection for Social Media Hackers Pred...CSEIJJournal
In machine learning, the intelligence of a developed model is greatly influenced by the dataset used for the
target domain on which the developed model will be deployed. Social media platform has experienced
more of hackers’ attacks on the platform in recent time. To identify a hacker on the platform, there are two
possible ways. The first is to use the activities of the user while the second is to use the supplied details the
user registered the account with. To adequately identify a social media user as hacker proactively, there
are relevant user details called features that can be used to determine whether a social media user is a
hacker or not. In this paper, an exploratory data analysis was carried out to determine the best features
that can be used by a predictive model to proactively identify hackers on the social media platform. A web
crawler was developed to mine the user dataset on which exploratory data analysis was carried out to
select the best features for the dataset which could be used to correctly identify a hacker on a social media
platform.
EXPLORATORY DATA ANALYSIS AND FEATURE SELECTION FOR SOCIAL MEDIA HACKERS PRED...CSEIJJournal
In machine learning, the intelligence of a developed model is greatly influenced by the dataset used for the
target domain on which the developed model will be deployed. Social media platform has experienced
more of hackers’ attacks on the platform in recent time. To identify a hacker on the platform, there are two
possible ways. The first is to use the activities of the user while the second is to use the supplied details the
user registered the account with. To adequately identify a social media user as hacker proactively, there
are relevant user details called features that can be used to determine whether a social media user is a
hacker or not. In this paper, an exploratory data analysis was carried out to determine the best features
that can be used by a predictive model to proactively identify hackers on the social media platform. A web
crawler was developed to mine the user dataset on which exploratory data analysis was carried out to
select the best features for the dataset which could be used to correctly identify a hacker on a social media
platform.
Exploring machine learning techniques for fake profile detection in online so...IJECEIAES
The online social network is the largest network, more than 4 billion users use social media and with its rapid growth, the risk of maintaining the integrity of data has tremendously increased. There are several kinds of security challenges in online social networks (OSNs). Many abominable behaviors try to hack social sites and misuse the data available on these sites. Therefore, protection against such behaviors has become an essential requirement. Though there are many types of security threats in online social networks but, one of the significant threats is the fake profile. Fake profiles are created intentionally with certain motives, and such profiles may be targeted to steal or acquire sensitive information and/or spread rumors on online social networks with specific motives. Fake profiles are primarily used to steal or extract information by means of friendly interaction online and/or misusing online data available on social sites. Thus, fake profile detection in social media networks is attracting the attention of researchers. This paper aims to discuss various machine learning (ML) methods used by researchers for fake profile detection to explore the further possibility of improvising the machine learning models for speedy results.
Botnet Detection in Online-social NetworkRubal Sagwal
Botnet, Bot master, Command and Control Server, States for Bots, Types of attacks, most wanted bots, Botnet life cycle, botnet topology, Social botnet.
An Automated Model to Detect Fake Profiles and botnets in Online Social Netwo...IOSR Journals
This document discusses an automated model for detecting fake profiles and botnets in online social networks. It begins with background on the prevalence of fake accounts, which can compromise user privacy and security. Next, it reviews related work on using data hiding techniques like steganography and watermarking to embed information in profile pictures in order to identify suspicious accounts. The proposed model aims to automatically detect fake profiles and botnets to replace current manual methods that are costly and labor-intensive.
1) The document proposes an automated model to detect fake profiles and botnets on online social networks using steganography and watermarking techniques.
2) It describes embedding unique information like a user's email or username into profile pictures during upload using watermarking. This allows detecting stolen pictures used for fake profiles.
3) The model is extended to also search uploaded pictures against billions of online images to detect multiple uses of the same picture for different profiles, as watermarking alone may fail if the picture is edited. Detected users must then prove ownership rights to the picture.
Detecting HTTP Botnet using Artificial Immune System (AIS)sadique_ghitm
This document proposes a new framework for detecting HTTP botnets using an Artificial Immune System (AIS). AIS is a bio-inspired model that applies concepts from the human immune system to solve information security problems. The proposed framework uses AIS techniques to detect malicious activities like spamming and port scanning on networks infected with HTTP bots. Experimental evaluations showed the approach can successfully detect HTTP botnet activities with high efficiency and low false positive rates.
Retrieving Hidden Friends a Collusion Privacy Attack against Online Friend Se...ijtsrd
Online Social Networks OSNs are providing a diversity of application for human users to network through families, friends and even strangers. One of such application, friend search engine, allows the universal public to inquiry individual client friend lists and has been gaining popularity recently. Proper design, this application may incorrectly disclose client private relationship information. Existing work has a privacy perpetuation clarification that can effectively boost OSNs' sociability while protecting users' friendship privacy against attacks launched by individual malicious requestors. In this project proposed an advanced collusion attack, where a victim user's friendship privacy can be compromise from side to side a series of cautiously designed queries coordinately launched by multiple malicious requestors. The result of the proposed collusion attack is validate through synthetic and real world social network data sets. The project on the advanced collusion attacks will help us design a more vigorous and securer friend search engine on OSNs in the near future. R. Brintha | H. Parveen Bagum "Retrieving Hidden Friends a Collusion Privacy Attack against Online Friend Search Engine" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-4 , June 2020, URL: https://www.ijtsrd.com/papers/ijtsrd31687.pdf Paper Url :https://www.ijtsrd.com/computer-science/world-wide-web/31687/retrieving-hidden-friends-a-collusion-privacy-attack-against-online-friend-search-engine/r-brintha
Exploratory Data Analysis and Feature Selection for Social Media Hackers Pred...CSEIJJournal
In machine learning, the intelligence of a developed model is greatly influenced by the dataset used for the
target domain on which the developed model will be deployed. Social media platform has experienced
more of hackers’ attacks on the platform in recent time. To identify a hacker on the platform, there are two
possible ways. The first is to use the activities of the user while the second is to use the supplied details the
user registered the account with. To adequately identify a social media user as hacker proactively, there
are relevant user details called features that can be used to determine whether a social media user is a
hacker or not. In this paper, an exploratory data analysis was carried out to determine the best features
that can be used by a predictive model to proactively identify hackers on the social media platform. A web
crawler was developed to mine the user dataset on which exploratory data analysis was carried out to
select the best features for the dataset which could be used to correctly identify a hacker on a social media
platform.
EXPLORATORY DATA ANALYSIS AND FEATURE SELECTION FOR SOCIAL MEDIA HACKERS PRED...CSEIJJournal
In machine learning, the intelligence of a developed model is greatly influenced by the dataset used for the
target domain on which the developed model will be deployed. Social media platform has experienced
more of hackers’ attacks on the platform in recent time. To identify a hacker on the platform, there are two
possible ways. The first is to use the activities of the user while the second is to use the supplied details the
user registered the account with. To adequately identify a social media user as hacker proactively, there
are relevant user details called features that can be used to determine whether a social media user is a
hacker or not. In this paper, an exploratory data analysis was carried out to determine the best features
that can be used by a predictive model to proactively identify hackers on the social media platform. A web
crawler was developed to mine the user dataset on which exploratory data analysis was carried out to
select the best features for the dataset which could be used to correctly identify a hacker on a social media
platform.
Exploring machine learning techniques for fake profile detection in online so...IJECEIAES
The online social network is the largest network, more than 4 billion users use social media and with its rapid growth, the risk of maintaining the integrity of data has tremendously increased. There are several kinds of security challenges in online social networks (OSNs). Many abominable behaviors try to hack social sites and misuse the data available on these sites. Therefore, protection against such behaviors has become an essential requirement. Though there are many types of security threats in online social networks but, one of the significant threats is the fake profile. Fake profiles are created intentionally with certain motives, and such profiles may be targeted to steal or acquire sensitive information and/or spread rumors on online social networks with specific motives. Fake profiles are primarily used to steal or extract information by means of friendly interaction online and/or misusing online data available on social sites. Thus, fake profile detection in social media networks is attracting the attention of researchers. This paper aims to discuss various machine learning (ML) methods used by researchers for fake profile detection to explore the further possibility of improvising the machine learning models for speedy results.
Botnet Detection in Online-social NetworkRubal Sagwal
Botnet, Bot master, Command and Control Server, States for Bots, Types of attacks, most wanted bots, Botnet life cycle, botnet topology, Social botnet.
An Automated Model to Detect Fake Profiles and botnets in Online Social Netwo...IOSR Journals
This document discusses an automated model for detecting fake profiles and botnets in online social networks. It begins with background on the prevalence of fake accounts, which can compromise user privacy and security. Next, it reviews related work on using data hiding techniques like steganography and watermarking to embed information in profile pictures in order to identify suspicious accounts. The proposed model aims to automatically detect fake profiles and botnets to replace current manual methods that are costly and labor-intensive.
1) The document proposes an automated model to detect fake profiles and botnets on online social networks using steganography and watermarking techniques.
2) It describes embedding unique information like a user's email or username into profile pictures during upload using watermarking. This allows detecting stolen pictures used for fake profiles.
3) The model is extended to also search uploaded pictures against billions of online images to detect multiple uses of the same picture for different profiles, as watermarking alone may fail if the picture is edited. Detected users must then prove ownership rights to the picture.
Detecting HTTP Botnet using Artificial Immune System (AIS)sadique_ghitm
This document proposes a new framework for detecting HTTP botnets using an Artificial Immune System (AIS). AIS is a bio-inspired model that applies concepts from the human immune system to solve information security problems. The proposed framework uses AIS techniques to detect malicious activities like spamming and port scanning on networks infected with HTTP bots. Experimental evaluations showed the approach can successfully detect HTTP botnet activities with high efficiency and low false positive rates.
Retrieving Hidden Friends a Collusion Privacy Attack against Online Friend Se...ijtsrd
Online Social Networks OSNs are providing a diversity of application for human users to network through families, friends and even strangers. One of such application, friend search engine, allows the universal public to inquiry individual client friend lists and has been gaining popularity recently. Proper design, this application may incorrectly disclose client private relationship information. Existing work has a privacy perpetuation clarification that can effectively boost OSNs' sociability while protecting users' friendship privacy against attacks launched by individual malicious requestors. In this project proposed an advanced collusion attack, where a victim user's friendship privacy can be compromise from side to side a series of cautiously designed queries coordinately launched by multiple malicious requestors. The result of the proposed collusion attack is validate through synthetic and real world social network data sets. The project on the advanced collusion attacks will help us design a more vigorous and securer friend search engine on OSNs in the near future. R. Brintha | H. Parveen Bagum "Retrieving Hidden Friends a Collusion Privacy Attack against Online Friend Search Engine" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-4 , June 2020, URL: https://www.ijtsrd.com/papers/ijtsrd31687.pdf Paper Url :https://www.ijtsrd.com/computer-science/world-wide-web/31687/retrieving-hidden-friends-a-collusion-privacy-attack-against-online-friend-search-engine/r-brintha
IRJET- Design and Development of a System for Predicting Threats using Data S...IRJET Journal
This document discusses the design and development of a system to predict threats using data from social media platforms. It aims to use natural language processing, machine learning algorithms, and data analytics on social media data from platforms like Facebook, Twitter, and Google Trends to identify upcoming threats. The system would categorize data into categories like toxic, severe toxic, obscene, insult, threat, and identity hate to predict threat levels. It would analyze data from various sources in real-time and predict threat levels for different regions as low, moderate, or high based on the population. The methodology involves collecting, preprocessing, and analyzing social media data using algorithms like CNN and Word2Vec for classification and sentiment analysis.
BullyNet is a three-phase algorithm that detects cyberbullies on Twitter. It first constructs a cyberbullying signed network (SN) by analyzing tweets and their contexts to determine sentiment and assign bullying scores to connections between users. It then proposes a centrality measure called attitude and merit (A&M) to identify cyberbullies from the SN. The algorithm was tested on a dataset of 5.6 million tweets and effectively detected cyberbullies with high accuracy while scaling to large numbers of tweets.
Social media websites are becoming more prevalent on the Internet. Sites, such as Twitter, Facebook, and Instagram, spend significantly more of their time on users online. People in social media share thoughts, views, and facts and create new acquaintances. Social media sites supply users with a great deal of useful information. This enormous quantity of social media information invites hackers to abuse data. These hackers establish fraudulent profiles for actual people and distribute useless material. The material on spam might include commercials and harmful URLs that disrupt natural users. This spam content is a massive problem in social networks. Spam identification is a vital procedure on social media networking platforms. In this paper, we have proposed a spam detection artificial intelligence technique for Twitter social networks. In this approach, we employed a vector support machine, a neural artificial network, and a random forest technique to build a model. The results indicate that, compared with RF and ANN algorithms, the suggested support vector machine algorithm has the greatest precision, recall, and Fmeasure. The findings of this paper would be useful in monitoring and tracking social media shared photos for the identification of inappropriate content and forged images and to safeguard social media from digital threats and attacks.
IRJET - Real-Time Cyberbullying Analysis on Social Media using Machine Learni...IRJET Journal
This document presents a system for real-time analysis of cyberbullying on social media using machine learning and text mining. The system aims to detect abusive conversations and censor harmful words to protect victims. It uses an artificial neural network machine learning algorithm to analyze words that could psychologically affect individuals. The system identifies abusive words in posts and comments and replaces them with censored content. This aims to prevent innocent users from being exposed to depressing or criminal activities online. The document discusses the system architecture, including tools for sentiment analysis, monitoring discussions, identifying abusive words, and updating a word database. Diagrams show the data flow, use cases, and interactions between system components.
A Mitigation Technique For Internet Security Threat of Toolkits AttackCSCJournals
The development of attack toolkits conforms that cybercrime is driven primarily by financial motivations as noted from the significant profits made by both the developers and buyers. In this paper, an enhanced hybrid attack toolkit mitigation model was designed to tackle the economy of the attack toolkits using different techniques to discredit it. The mitigation looked into Zeus, a common and the most frequently used attack toolkit to discover the hidden information used by the attackers to launch attacks. This information helped in creating honey toolkits, honeybot and honeytokens. Honeybots are used to submit honeytoken to botmasters, who sells to the internet black market. Both the botmasters, his mules and buyers attempts to steal huge amount of money using the stolen credentials which includes both real and honeytokens and will be detected by an attack detector which sends an alert on any transaction involving the honeytokens. A reconfirmation process which is secured using enhanced RC6 cryptosystem is enacted. The reconfirmation message in plain text is securely encrypted into cipher text and transmitted from the bank to the legitimate account owner and vise visa. The result of the crypto analysis carried out on the encrypted text using RC6 encryption algorithm showed that the cipher text is not transparent.
Artificial Intelligence Approach for Covid Period StudyPalIRJET Journal
The document proposes the development of an AI chatbot named StudyPal that can serve as a virtual tutor for students. StudyPal would use techniques like active recall and mind mapping to teach students curriculum content for their grade and subject without needing an in-person teacher. The goal is for StudyPal to provide individualized attention to effectively communicate concepts to each student. StudyPal would be created using a federated learning model to maintain data privacy and address issues with internet connectivity. The document outlines the proposed design and development process for StudyPal.
The document describes a tool called the "Profanity Statistical Analyzer" that was developed to analyze webpages, social media posts, and blogs to detect and quantify the amount of profane or abusive language. The tool works by taking in content, tokenizing it, comparing the tokens to a dataset of abusive words, and reporting the results both as a percentage of abusive words and by highlighting which actual words were detected. The tool is meant to help users determine whether certain online content is appropriate for them to view by automatically analyzing the language used.
Vulnerabilities and attacks targeting social networks and industrial control ...ijcsa
Vulnerability is a weakness, shortcoming or flaw in the system or network infrastructure which can be used
by an attacker to harm the system, disrupt its normal operation and use it for his financial, competitive or
other motives or just for cyber escapades.
In this paper, we re-examined the various types of attacks on industrial control systems as well as on social
networking users. We have listed which all vulnerabilities were exploited for executing these attacks and
their effects on these systems and social networks. The focus will be mainly on the vulnerabilities that are
used in OSNs as the convertors which convert the social network into antisocial network and these
networks can be further used for the network attacks on the users associated with the victim user whereby
creating a consecutive chain of attacks on increasing number of social networking users. Another type of
attack, Stuxnet Attack which was originally designed to attack Iran’s nuclear facilities is also discussed
here which harms the system it controls by changing the code in that target system. The Stuxnet worm is a
very treacherous and hazardous means of attack and is the first of its kind as it allows the attacker to
manipulate real-time equipment.
Emerged computer interaction with humanity social computingijcsa
In the 21st century, everywhere people analyze & measure societal. The new trend to compute the societal is
known as social computing. The emerging trend of research focuses interaction of technologies with
humanity. This interaction can be either man machine interaction or human computer interaction. This
article conveys the brief description of social computing and social impact of computing into variant
environment. It optimises the interaction technology, ubiquitous computing and pervasive computing.
Subsequently affective computing is discussed with artificial intelligence to motivate the automation of
technology in social computing.
The Auto response system for legal consultation will provide the knowledge of cyber laws. The objective is to implement the legal consultant system service by using chat bot Technology. It was implemented based on the information of the offence, previous records of cyber crimes and under sections of INDIAN IT ACT 2008 and their penalty all the records are gathered. User will input the offence then the chat bot will take the keyword from that offence and search for the law for that particular offence or crime and it will show the penalties, sections, and imprisonment for that offence or crime. Nikita Bhanushali | Shruti Habibkar | Sagar Shah | Amol Dhumal | Radhika Fulzele "Auto Response System for Legal Consultation" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-4 , June 2020, URL: https://www.ijtsrd.com/papers/ijtsrd31045.pdf Paper Url :https://www.ijtsrd.com/engineering/computer-engineering/31045/auto-response-system-for-legal-consultation/nikita-bhanushali
This document discusses the risks of botnet attacks on smartphones. It begins by providing background on botnets and how they have evolved from PC-based to targeting smartphones. Common propagation methods for smartphone botnets include SMS, Bluetooth, NFC, and WiFi. The document then proposes a hybrid peer-to-peer system using WiFi as the communication medium to create a botnet that is difficult to detect. It argues that securing smartphones from botnet attacks is challenging given the variety of mobile architectures and increasing use of smartphones for sensitive tasks.
Face expressions, facial features, kinect sensor, face tracking SDK, neural n...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
BINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNINGIRJET Journal
This document discusses the development of a cyberharassment detection system to identify abusive content on social media platforms. It reviews related works that have used machine learning techniques like convolutional neural networks and transfer learning models to detect cyberbullying. The authors investigate four neural network optimizers - Rmsprop, Adam, Adadelta, and Adagrad - and find that Rmsprop achieved the highest accuracy of 98.45% at classifying harassing content. The goal of this research is to create an effective model for automatically detecting cyberharassment online.
A Machine Learning Ensemble Model for the Detection of Cyberbullyinggerogepatton
The pervasive use of social media platforms, such as Facebook, Instagram, and X, has significantly amplified
our electronic interconnectedness. Moreover, these platforms are now easily accessible from any location at
any given time. However, the increased popularity of social media has also led to cyberbullying.It is imperative
to address the need for finding, monitoring, and mitigating cyberbullying posts on social media platforms.
Motivated by this necessity, we present this paper to contribute to developing an automated system for
detecting binary labels of aggressive tweets.Our study has demonstrated remarkable performance compared to
previous experiments on the same dataset. We employed the stacking ensemble machine learning method,
utilizing four various feature extraction techniques to optimize performance within the stacking ensemble
learning framework. Combining five machine learning algorithms,Decision Trees, Random Forest, Linear
Support Vector Classification, Logistic Regression, and K-Nearest Neighbors into an ensemble method, we
achieved superior results compared to traditional machine learning classifier models. The stacking classifier
achieved a high accuracy rate of 94.00%, outperforming traditional machine learning models and surpassing
the results of prior experiments that utilized the same dataset. The outcomes of our experiments showcased an
accuracy rate of 0.94% in detection tweets as aggressive or non-aggressive.
A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYINGijaia
The pervasive use of social media platforms, such as Facebook, Instagram, and X, has significantly amplified
our electronic interconnectedness. Moreover, these platforms are now easily accessible from any location at
any given time. However, the increased popularity of social media has also led to cyberbullying.It is imperative
to address the need for finding, monitoring, and mitigating cyberbullying posts on social media platforms.
Motivated by this necessity, we present this paper to contribute to developing an automated system for
detecting binary labels of aggressive tweets.Our study has demonstrated remarkable performance compared to
previous experiments on the same dataset. We employed the stacking ensemble machine learning method,
utilizing four various feature extraction techniques to optimize performance within the stacking ensemble
learning framework. Combining five machine learning algorithms,Decision Trees, Random Forest, Linear
Support Vector Classification, Logistic Regression, and K-Nearest Neighbors into an ensemble method, we
achieved superior results compared to traditional machine learning classifier models. The stacking classifier
achieved a high accuracy rate of 94.00%, outperforming traditional machine learning models and surpassing
the results of prior experiments that utilized the same dataset. The outcomes of our experiments showcased an
accuracy rate of 0.94% in detection tweets as aggressive or non-aggressive.
A Machine Learning Ensemble Model for the Detection of Cyberbullyinggerogepatton
The pervasive use of social media platforms, such as Facebook, Instagram, and X, has significantly amplified
our electronic interconnectedness. Moreover, these platforms are now easily accessible from any location at
any given time. However, the increased popularity of social media has also led to cyberbullying.It is imperative
to address the need for finding, monitoring, and mitigating cyberbullying posts on social media platforms.
Motivated by this necessity, we present this paper to contribute to developing an automated system for
detecting binary labels of aggressive tweets.Our study has demonstrated remarkable performance compared to
previous experiments on the same dataset. We employed the stacking ensemble machine learning method,
utilizing four various feature extraction techniques to optimize performance within the stacking ensemble
learning framework. Combining five machine learning algorithms,Decision Trees, Random Forest, Linear
Support Vector Classification, Logistic Regression, and K-Nearest Neighbors into an ensemble method, we
achieved superior results compared to traditional machine learning classifier models. The stacking classifier
achieved a high accuracy rate of 94.00%, outperforming traditional machine learning models and surpassing
the results of prior experiments that utilized the same dataset. The outcomes of our experiments showcased an
accuracy rate of 0.94% in detection tweets as aggressive or non-aggressive.
How does fakenews spread understanding pathways of disinformation spread thro...Araz Taeihagh
What are the pathways for spreading disinformation on social media platforms? This article addresses this question by collecting, categorising, and situating an extensive body of research on how application programming interfaces (APIs) provided by social media platforms facilitate the spread of disinformation. We first examine the landscape of official social media APIs, then perform quantitative research on the open-source code repositories GitHub and GitLab to understand the usage patterns of these APIs. By inspecting the code repositories, we classify developers' usage of the APIs as official and unofficial, and further develop a four-stage framework characterising pathways for spreading disinformation on social media platforms. We further highlight how the stages in the framework were activated during the 2016 US Presidential Elections, before providing policy recommendations for issues relating to access to APIs, algorithmic content, advertisements, and suggest rapid response to coordinate campaigns, development of collaborative, and participatory approaches as well as government stewardship in the regulation of social media platforms.
Citizen sensor data mining, social media analytics, and development-centric web applications were discussed. Key points included:
1. Citizen sensing allows ordinary people to observe, report, and share information using mobile devices and social networks. This creates citizen-sensor networks with potential for disseminating social signals.
2. Social media plays important roles in activism, journalism, business intelligence, and global development. Development-centric platforms like Ushahidi and Sahana support collaboration and crisis response.
3. Understanding social media requires studying content, people, and networks through a spatio-temporal-thematic lens using metadata about locations, times, topics, identities, relationships, and information flow.
The advancement of Information Technology has hastened the ability to disseminate information across the globe. In particular, the recent trends in ‘Social Networking’ have led to a spark in personally sensitive information being published on the World Wide Web. While such socially active websites are creative tools for expressing one’s personality it also entails serious privacy concerns. Thus, Social Networking websites could be termed a double edged sword. It is important for the law to keep abreast of these developments in technology. The purpose of this paper is to demonstrate the limits of extending existing laws to battle privacy intrusions in the Internet especially in the context of social networking. It is suggested that privacy specific legislation is the most appropriate means of protecting online privacy. In doing so it is important to maintain a balance between the competing right of expression, the failure of which may hinder the reaping of benefits offered by Internet technology
DESIGN OF A MINIATURE RECTANGULAR PATCH ANTENNA FOR KU BAND APPLICATIONSijasa
A significant portion of communication devices employs microstrip antennas because of their compact size,
low profile, and ability to conform to both planar and non-planar surfaces. To achieve this, we present a
miniature inset-fed rectangular patch antenna using partial ground plane for Ku band applications. The
proposed antenna design used an operating frequency of 15.5 GHz, a FR4 substrate with a dielectric
constant of 4.3, and a thickness of 1.4 mm. It is fed by a 50 Ω inset feedline. Computer simulation
technology (CST) software is used to design, simulate, and analyze. The simulation yields the antenna
performance parameters, including return loss (S11), bandwidth, VSWR, gain, directivity, and radiation
efficiency. The simulation findings revealed that the proposed antenna resonated at 15.5 GHz, with a
return loss of -22.312 dB, a bandwidth of 2.73 GHz (2730 MHz), VSWR of 1.17, a gain of 3.843 dBi, a
directivity of 5.926 dBi, and an antenna efficiency of -2.083 dB (61.901%).
SMART SOUND SYSTEM APPLIED FOR THE EXTENSIVE CARE OF PEOPLE WITH HEARING IMPA...ijasa
We, as normal people, have access to a potent communication tool, which is sound. Although we can continuously gather, analyse, and interpret sounds thanks to our sense of hearing, it can be challenging for people with hearing impairment to perceive their surroundings through sound. Also known as PWHI (People with Hearing Impairment). Auditory/phonic impairment is one of the most prevailing sensory deficits in humans at present. Fortunately, there is room to apply a solution to this issue, given the development of technology. Our project involves capturing ambient sounds from the user’s surroundings and notifying the user through a mobile application using IoT and Deep Learning. Its architecture offers sound recognition using a tool, such as a microphone, to capture sounds from the user's surroundings. These sounds are identified and categorized as ambient sounds, like a doorbell, baby cry, and dog barking; as well as emergency-related sounds, such as alarms, sirens, et
More Related Content
Similar to A CONCEPTUAL FRAMEWORK OF A DETECTIVE MODEL FOR SOCIAL BOT CLASSIFICATION
IRJET- Design and Development of a System for Predicting Threats using Data S...IRJET Journal
This document discusses the design and development of a system to predict threats using data from social media platforms. It aims to use natural language processing, machine learning algorithms, and data analytics on social media data from platforms like Facebook, Twitter, and Google Trends to identify upcoming threats. The system would categorize data into categories like toxic, severe toxic, obscene, insult, threat, and identity hate to predict threat levels. It would analyze data from various sources in real-time and predict threat levels for different regions as low, moderate, or high based on the population. The methodology involves collecting, preprocessing, and analyzing social media data using algorithms like CNN and Word2Vec for classification and sentiment analysis.
BullyNet is a three-phase algorithm that detects cyberbullies on Twitter. It first constructs a cyberbullying signed network (SN) by analyzing tweets and their contexts to determine sentiment and assign bullying scores to connections between users. It then proposes a centrality measure called attitude and merit (A&M) to identify cyberbullies from the SN. The algorithm was tested on a dataset of 5.6 million tweets and effectively detected cyberbullies with high accuracy while scaling to large numbers of tweets.
Social media websites are becoming more prevalent on the Internet. Sites, such as Twitter, Facebook, and Instagram, spend significantly more of their time on users online. People in social media share thoughts, views, and facts and create new acquaintances. Social media sites supply users with a great deal of useful information. This enormous quantity of social media information invites hackers to abuse data. These hackers establish fraudulent profiles for actual people and distribute useless material. The material on spam might include commercials and harmful URLs that disrupt natural users. This spam content is a massive problem in social networks. Spam identification is a vital procedure on social media networking platforms. In this paper, we have proposed a spam detection artificial intelligence technique for Twitter social networks. In this approach, we employed a vector support machine, a neural artificial network, and a random forest technique to build a model. The results indicate that, compared with RF and ANN algorithms, the suggested support vector machine algorithm has the greatest precision, recall, and Fmeasure. The findings of this paper would be useful in monitoring and tracking social media shared photos for the identification of inappropriate content and forged images and to safeguard social media from digital threats and attacks.
IRJET - Real-Time Cyberbullying Analysis on Social Media using Machine Learni...IRJET Journal
This document presents a system for real-time analysis of cyberbullying on social media using machine learning and text mining. The system aims to detect abusive conversations and censor harmful words to protect victims. It uses an artificial neural network machine learning algorithm to analyze words that could psychologically affect individuals. The system identifies abusive words in posts and comments and replaces them with censored content. This aims to prevent innocent users from being exposed to depressing or criminal activities online. The document discusses the system architecture, including tools for sentiment analysis, monitoring discussions, identifying abusive words, and updating a word database. Diagrams show the data flow, use cases, and interactions between system components.
A Mitigation Technique For Internet Security Threat of Toolkits AttackCSCJournals
The development of attack toolkits conforms that cybercrime is driven primarily by financial motivations as noted from the significant profits made by both the developers and buyers. In this paper, an enhanced hybrid attack toolkit mitigation model was designed to tackle the economy of the attack toolkits using different techniques to discredit it. The mitigation looked into Zeus, a common and the most frequently used attack toolkit to discover the hidden information used by the attackers to launch attacks. This information helped in creating honey toolkits, honeybot and honeytokens. Honeybots are used to submit honeytoken to botmasters, who sells to the internet black market. Both the botmasters, his mules and buyers attempts to steal huge amount of money using the stolen credentials which includes both real and honeytokens and will be detected by an attack detector which sends an alert on any transaction involving the honeytokens. A reconfirmation process which is secured using enhanced RC6 cryptosystem is enacted. The reconfirmation message in plain text is securely encrypted into cipher text and transmitted from the bank to the legitimate account owner and vise visa. The result of the crypto analysis carried out on the encrypted text using RC6 encryption algorithm showed that the cipher text is not transparent.
Artificial Intelligence Approach for Covid Period StudyPalIRJET Journal
The document proposes the development of an AI chatbot named StudyPal that can serve as a virtual tutor for students. StudyPal would use techniques like active recall and mind mapping to teach students curriculum content for their grade and subject without needing an in-person teacher. The goal is for StudyPal to provide individualized attention to effectively communicate concepts to each student. StudyPal would be created using a federated learning model to maintain data privacy and address issues with internet connectivity. The document outlines the proposed design and development process for StudyPal.
The document describes a tool called the "Profanity Statistical Analyzer" that was developed to analyze webpages, social media posts, and blogs to detect and quantify the amount of profane or abusive language. The tool works by taking in content, tokenizing it, comparing the tokens to a dataset of abusive words, and reporting the results both as a percentage of abusive words and by highlighting which actual words were detected. The tool is meant to help users determine whether certain online content is appropriate for them to view by automatically analyzing the language used.
Vulnerabilities and attacks targeting social networks and industrial control ...ijcsa
Vulnerability is a weakness, shortcoming or flaw in the system or network infrastructure which can be used
by an attacker to harm the system, disrupt its normal operation and use it for his financial, competitive or
other motives or just for cyber escapades.
In this paper, we re-examined the various types of attacks on industrial control systems as well as on social
networking users. We have listed which all vulnerabilities were exploited for executing these attacks and
their effects on these systems and social networks. The focus will be mainly on the vulnerabilities that are
used in OSNs as the convertors which convert the social network into antisocial network and these
networks can be further used for the network attacks on the users associated with the victim user whereby
creating a consecutive chain of attacks on increasing number of social networking users. Another type of
attack, Stuxnet Attack which was originally designed to attack Iran’s nuclear facilities is also discussed
here which harms the system it controls by changing the code in that target system. The Stuxnet worm is a
very treacherous and hazardous means of attack and is the first of its kind as it allows the attacker to
manipulate real-time equipment.
Emerged computer interaction with humanity social computingijcsa
In the 21st century, everywhere people analyze & measure societal. The new trend to compute the societal is
known as social computing. The emerging trend of research focuses interaction of technologies with
humanity. This interaction can be either man machine interaction or human computer interaction. This
article conveys the brief description of social computing and social impact of computing into variant
environment. It optimises the interaction technology, ubiquitous computing and pervasive computing.
Subsequently affective computing is discussed with artificial intelligence to motivate the automation of
technology in social computing.
The Auto response system for legal consultation will provide the knowledge of cyber laws. The objective is to implement the legal consultant system service by using chat bot Technology. It was implemented based on the information of the offence, previous records of cyber crimes and under sections of INDIAN IT ACT 2008 and their penalty all the records are gathered. User will input the offence then the chat bot will take the keyword from that offence and search for the law for that particular offence or crime and it will show the penalties, sections, and imprisonment for that offence or crime. Nikita Bhanushali | Shruti Habibkar | Sagar Shah | Amol Dhumal | Radhika Fulzele "Auto Response System for Legal Consultation" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-4 , June 2020, URL: https://www.ijtsrd.com/papers/ijtsrd31045.pdf Paper Url :https://www.ijtsrd.com/engineering/computer-engineering/31045/auto-response-system-for-legal-consultation/nikita-bhanushali
This document discusses the risks of botnet attacks on smartphones. It begins by providing background on botnets and how they have evolved from PC-based to targeting smartphones. Common propagation methods for smartphone botnets include SMS, Bluetooth, NFC, and WiFi. The document then proposes a hybrid peer-to-peer system using WiFi as the communication medium to create a botnet that is difficult to detect. It argues that securing smartphones from botnet attacks is challenging given the variety of mobile architectures and increasing use of smartphones for sensitive tasks.
Face expressions, facial features, kinect sensor, face tracking SDK, neural n...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
BINARY TEXT CLASSIFICATION OF CYBER HARASSMENT USING DEEP LEARNINGIRJET Journal
This document discusses the development of a cyberharassment detection system to identify abusive content on social media platforms. It reviews related works that have used machine learning techniques like convolutional neural networks and transfer learning models to detect cyberbullying. The authors investigate four neural network optimizers - Rmsprop, Adam, Adadelta, and Adagrad - and find that Rmsprop achieved the highest accuracy of 98.45% at classifying harassing content. The goal of this research is to create an effective model for automatically detecting cyberharassment online.
A Machine Learning Ensemble Model for the Detection of Cyberbullyinggerogepatton
The pervasive use of social media platforms, such as Facebook, Instagram, and X, has significantly amplified
our electronic interconnectedness. Moreover, these platforms are now easily accessible from any location at
any given time. However, the increased popularity of social media has also led to cyberbullying.It is imperative
to address the need for finding, monitoring, and mitigating cyberbullying posts on social media platforms.
Motivated by this necessity, we present this paper to contribute to developing an automated system for
detecting binary labels of aggressive tweets.Our study has demonstrated remarkable performance compared to
previous experiments on the same dataset. We employed the stacking ensemble machine learning method,
utilizing four various feature extraction techniques to optimize performance within the stacking ensemble
learning framework. Combining five machine learning algorithms,Decision Trees, Random Forest, Linear
Support Vector Classification, Logistic Regression, and K-Nearest Neighbors into an ensemble method, we
achieved superior results compared to traditional machine learning classifier models. The stacking classifier
achieved a high accuracy rate of 94.00%, outperforming traditional machine learning models and surpassing
the results of prior experiments that utilized the same dataset. The outcomes of our experiments showcased an
accuracy rate of 0.94% in detection tweets as aggressive or non-aggressive.
A MACHINE LEARNING ENSEMBLE MODEL FOR THE DETECTION OF CYBERBULLYINGijaia
The pervasive use of social media platforms, such as Facebook, Instagram, and X, has significantly amplified
our electronic interconnectedness. Moreover, these platforms are now easily accessible from any location at
any given time. However, the increased popularity of social media has also led to cyberbullying.It is imperative
to address the need for finding, monitoring, and mitigating cyberbullying posts on social media platforms.
Motivated by this necessity, we present this paper to contribute to developing an automated system for
detecting binary labels of aggressive tweets.Our study has demonstrated remarkable performance compared to
previous experiments on the same dataset. We employed the stacking ensemble machine learning method,
utilizing four various feature extraction techniques to optimize performance within the stacking ensemble
learning framework. Combining five machine learning algorithms,Decision Trees, Random Forest, Linear
Support Vector Classification, Logistic Regression, and K-Nearest Neighbors into an ensemble method, we
achieved superior results compared to traditional machine learning classifier models. The stacking classifier
achieved a high accuracy rate of 94.00%, outperforming traditional machine learning models and surpassing
the results of prior experiments that utilized the same dataset. The outcomes of our experiments showcased an
accuracy rate of 0.94% in detection tweets as aggressive or non-aggressive.
A Machine Learning Ensemble Model for the Detection of Cyberbullyinggerogepatton
The pervasive use of social media platforms, such as Facebook, Instagram, and X, has significantly amplified
our electronic interconnectedness. Moreover, these platforms are now easily accessible from any location at
any given time. However, the increased popularity of social media has also led to cyberbullying.It is imperative
to address the need for finding, monitoring, and mitigating cyberbullying posts on social media platforms.
Motivated by this necessity, we present this paper to contribute to developing an automated system for
detecting binary labels of aggressive tweets.Our study has demonstrated remarkable performance compared to
previous experiments on the same dataset. We employed the stacking ensemble machine learning method,
utilizing four various feature extraction techniques to optimize performance within the stacking ensemble
learning framework. Combining five machine learning algorithms,Decision Trees, Random Forest, Linear
Support Vector Classification, Logistic Regression, and K-Nearest Neighbors into an ensemble method, we
achieved superior results compared to traditional machine learning classifier models. The stacking classifier
achieved a high accuracy rate of 94.00%, outperforming traditional machine learning models and surpassing
the results of prior experiments that utilized the same dataset. The outcomes of our experiments showcased an
accuracy rate of 0.94% in detection tweets as aggressive or non-aggressive.
How does fakenews spread understanding pathways of disinformation spread thro...Araz Taeihagh
What are the pathways for spreading disinformation on social media platforms? This article addresses this question by collecting, categorising, and situating an extensive body of research on how application programming interfaces (APIs) provided by social media platforms facilitate the spread of disinformation. We first examine the landscape of official social media APIs, then perform quantitative research on the open-source code repositories GitHub and GitLab to understand the usage patterns of these APIs. By inspecting the code repositories, we classify developers' usage of the APIs as official and unofficial, and further develop a four-stage framework characterising pathways for spreading disinformation on social media platforms. We further highlight how the stages in the framework were activated during the 2016 US Presidential Elections, before providing policy recommendations for issues relating to access to APIs, algorithmic content, advertisements, and suggest rapid response to coordinate campaigns, development of collaborative, and participatory approaches as well as government stewardship in the regulation of social media platforms.
Citizen sensor data mining, social media analytics, and development-centric web applications were discussed. Key points included:
1. Citizen sensing allows ordinary people to observe, report, and share information using mobile devices and social networks. This creates citizen-sensor networks with potential for disseminating social signals.
2. Social media plays important roles in activism, journalism, business intelligence, and global development. Development-centric platforms like Ushahidi and Sahana support collaboration and crisis response.
3. Understanding social media requires studying content, people, and networks through a spatio-temporal-thematic lens using metadata about locations, times, topics, identities, relationships, and information flow.
The advancement of Information Technology has hastened the ability to disseminate information across the globe. In particular, the recent trends in ‘Social Networking’ have led to a spark in personally sensitive information being published on the World Wide Web. While such socially active websites are creative tools for expressing one’s personality it also entails serious privacy concerns. Thus, Social Networking websites could be termed a double edged sword. It is important for the law to keep abreast of these developments in technology. The purpose of this paper is to demonstrate the limits of extending existing laws to battle privacy intrusions in the Internet especially in the context of social networking. It is suggested that privacy specific legislation is the most appropriate means of protecting online privacy. In doing so it is important to maintain a balance between the competing right of expression, the failure of which may hinder the reaping of benefits offered by Internet technology
Similar to A CONCEPTUAL FRAMEWORK OF A DETECTIVE MODEL FOR SOCIAL BOT CLASSIFICATION (20)
DESIGN OF A MINIATURE RECTANGULAR PATCH ANTENNA FOR KU BAND APPLICATIONSijasa
A significant portion of communication devices employs microstrip antennas because of their compact size,
low profile, and ability to conform to both planar and non-planar surfaces. To achieve this, we present a
miniature inset-fed rectangular patch antenna using partial ground plane for Ku band applications. The
proposed antenna design used an operating frequency of 15.5 GHz, a FR4 substrate with a dielectric
constant of 4.3, and a thickness of 1.4 mm. It is fed by a 50 Ω inset feedline. Computer simulation
technology (CST) software is used to design, simulate, and analyze. The simulation yields the antenna
performance parameters, including return loss (S11), bandwidth, VSWR, gain, directivity, and radiation
efficiency. The simulation findings revealed that the proposed antenna resonated at 15.5 GHz, with a
return loss of -22.312 dB, a bandwidth of 2.73 GHz (2730 MHz), VSWR of 1.17, a gain of 3.843 dBi, a
directivity of 5.926 dBi, and an antenna efficiency of -2.083 dB (61.901%).
SMART SOUND SYSTEM APPLIED FOR THE EXTENSIVE CARE OF PEOPLE WITH HEARING IMPA...ijasa
We, as normal people, have access to a potent communication tool, which is sound. Although we can continuously gather, analyse, and interpret sounds thanks to our sense of hearing, it can be challenging for people with hearing impairment to perceive their surroundings through sound. Also known as PWHI (People with Hearing Impairment). Auditory/phonic impairment is one of the most prevailing sensory deficits in humans at present. Fortunately, there is room to apply a solution to this issue, given the development of technology. Our project involves capturing ambient sounds from the user’s surroundings and notifying the user through a mobile application using IoT and Deep Learning. Its architecture offers sound recognition using a tool, such as a microphone, to capture sounds from the user's surroundings. These sounds are identified and categorized as ambient sounds, like a doorbell, baby cry, and dog barking; as well as emergency-related sounds, such as alarms, sirens, et
AN INTELLIGENT AND DATA-DRIVEN MOBILE VOLUNTEER EVENT MANAGEMENT PLATFORM USI...ijasa
In Lewis and Clark High School’s Key Club, meetings are always held in a crowded classroom. The
system of event sign-up is inefficient and hinders members from joining events. This has led to students
becoming discouraged from joining Key Club and often resulted in a lack of volunteers for important
events. The club needed a more efficient way of connecting volunteers with volunteering opportunities. To
solve this problem, we developed a VolunteerMatch Mobile application using Dart and Flutter framework
for Key Club to use. The next steps will be to add a volunteer event recommendation and matching feature,
utilizing the results from the research on machine learning models and algorithms in this paper.
A STUDY OF IOT BASED REAL-TIME SOLAR POWER REMOTE MONITORING SYSTEMijasa
We have Developed an IoT-based real-time solar power monitoring system in this paper. It seeks an opensource IoT solution that can collect real-time data and continuously monitor the power output and environmental conditions of a photovoltaic panel.The Objective of this work is to continuously monitor the status of various parameters associated with solar systems through sensors without visiting manually, saving time and ensures efficient power output from PV panels while monitoring for faulty solar panels, weather conditionsand other such issues that affect solar effectiveness.Manually, the user must use a multimeter to determine what value of measurement of the system is appropriate for appliance consumers, which is difficult for the larger System. But the Solar Energy Monitoring system is designed to make it easier for users to use the solar system.This system is comprised of a microcontroller (Node MCU), a PV panel, sensors (INA219 Current Module, Digital Temperature Sensor, LDR), a Battery Charger Module, and a battery. The data from the PV panels and other appliances are sent to the cloud (Thingspeak) via the internet using IoT technology and a Wi-Fi module (NodeMCU). It also allows users in remote areas to monitor the parameters of the solar power plant using connected devices. The user can view the current, previous, and average parameters of the solar PV system, such as voltage, current, temperature, and light intensity using a Graphical User Interface. This will facilitate fault detection and maintenance of the solar power plant easier and saves time.
SENSOR BASED SMART IRRIGATION SYSTEM WITH MONITORING AND CONTROLLING USING IN...ijasa
This document presents a sensor-based smart irrigation system using IoT. The system uses soil moisture, temperature, and humidity sensors connected to a NodeMCU microcontroller. The sensor data is sent to a cloud server (ThingSpeak) and displayed as graphs on a website. A web page allows users to control a water pump remotely. The system was tested on a field over one day, recording sensor data and pump status in the morning, afternoon and night. Test results showed the pump turned on when soil moisture fell below a threshold and off when above a threshold, conserving water. The smart irrigation system allows remote monitoring and control to help farmers irrigate crops efficiently with minimal human effort or water waste.
COMPARISON OF BIT ERROR RATE PERFORMANCE OF VARIOUS DIGITAL MODULATION SCHEME...ijasa
This document compares the bit error rate (BER) performance of different digital modulation schemes (BPSK, QPSK, 16-QAM) over AWGN and Rayleigh fading channels using Simulink simulations. It finds that BPSK outperforms QPSK and 16-QAM in both channels. The BER is evaluated for these modulation schemes using two equalization techniques: constant modulus algorithm (CMA) and maximum likelihood sequence estimation (MLSE). According to the results, BPSK has better BER performance than QPSK and 16-QAM when using either equalizer, especially at lower SNR values. CMA equalization works better than MLSE equalization for all modulation schemes based on the BER values obtained.
PERFORMANCE OF CONVOLUTION AND CRC CHANNEL ENCODED V-BLAST 4×4 MIMO MCCDMA WI...ijasa
This document analyzes the performance of a 4x4 Vertical Bell Labs Layered Space-Time (V-Blast) multiple-input multiple-output multi-carrier code division multiple access (MIMO MC-CDMA) wireless communication system using different digital modulation schemes. The system uses minimum mean square error (MMSE) signal detection and 1/2-rated convolution and cyclic redundancy check (CRC) channel encoding. Simulation results show that binary phase-shift keying (BPSK) modulation outperforms differential phase-shift keying (DPSK), quadrature phase-shift keying (QPSK), and 16-quadrature amplitude modulation (QAM), achieving the lowest bit error rate (BER) especially at
A SCRUTINY TO ATTACK ISSUES AND SECURITY CHALLENGES IN CLOUD COMPUTINGijasa
Cloud computing is an anthology in which one or more computers are connected in a network. Cloud
computing is a cluster of lattice computing, autonomic computing and utility computing. Cloud provides an
on demand services to the users. Many numbers of users access the cloud to utilize the cloud resources.
The security is one the major problem in cloud computing. Hence security is a major issue in cloud
computing. Providing security is a major requirement of cloud computing. The study enclose all the
security issues and attack issues in cloud computing.
The International Journal of Ambient Systems and Applications (IJASA) ijasa
The International Journal of Ambient Systems and applications is a quarterly open access peer-reviewed journal that publishes articles which contribute new results in all areas of ambient Systems. The journal focuses on all technical and practical aspects of ambient Systems, networks, technologies and applications. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced ambient Systems and establishing new collaborations in these areas.Authors are solicited to contribute to this journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in ambient Systems.
A SCRUTINY TO ATTACK ISSUES AND SECURITY CHALLENGES IN CLOUD COMPUTINGijasa
Cloud computing is an anthology in which one or more computers are connected in a network. Cloud computing is a cluster of lattice computing, autonomic computing and utility computing. Cloud provides an on demand services to the users. Many numbers of users access the cloud to utilize the cloud resources. The security is one the major problem in cloud computing. Hence security is a major issue in cloud computing. Providing security is a major requirement of cloud computing. The study enclose all the security issues and attack issues in cloud computing.
TOWARD ORGANIC COMPUTING APPROACH FOR CYBERNETIC RESPONSIVE ENVIRONMENTijasa
The developpment of the Internet of Things (IoT) concept revives Responsive Environments (RE) technologies. Nowadays, the idea of a permanent connection between physical and digital world is technologically possible. The capillar Internet relates to the Internet extension into daily appliances such as they become actors of Internet like any hu-man. The parallel development of Machine-to-Machine
communications and Arti cial Intelligence (AI) technics start a new area of cybernetic. This paper presents an approach for Cybernetic Organism (Cyborg) for RE based on Organic Computing (OC). In such approach, each appli-ance is a part of an autonomic system in order to control a physical environment.The underlying idea is that such systems must have self-x properties in order to adapt their behavior to
external disturbances with a high-degree of autonomy.
A STUDY ON DEVELOPING A SMART ENVIRONMENT IN AGRICULTURAL IRRIGATION TECHNIQUEijasa
Maintaining a good irrigation system is a necessity in today’s water scarcity environment. This paper describes a new approach for automated Smart Irrigation (SIR) system in agricultural management. Using
various types of sensors in the crop field area, temperature and moisture value of the soil is monitored.Based on the sensed data, SIR will automatically decide about the necessary action for irrigation and also notifies the user. The system will also focus on the reduction of energy consumption by the sensors during communication.
A REVIEW ON DDOS PREVENTION AND DETECTION METHODOLOGYijasa
Denial of Service (DoS) or Distributed-Denial of Service (DDoS) is major threat to network security.
Network is collection of nodes that interconnect with each other for exchange the Information. This
information is required for that node is kept confidentially. Attacker in network computer captures this
information that is confidential and misuse the network. Hence security is one of the major issues. There
are one or many attacks in network. One of the major threats to internet service is DDoS (Distributed
denial of services) attack. DDoS attack is a malicious attempt to suspending or interrupting services to
target node. DDoS or DoS is an attempt to make network resource or the machine is unavailable to its
intended user. Many ideas are developed for avoiding the DDoS or DoS. DDoS happen in two ways
naturally or it may due to some botnets .Various schemes are developed defense against to this attack.
Main idea of this paper is present basis of DDoS attack. DDoS attack types, DDoS attack components,
survey on different mechanism to prevent DDoS
The smart mobile terminal operator platform Android is getting popular all over the world with its wide variety of applications and enormous use in numerous spheres of our daily life. Considering the fact of increasing demand of home security and automation, an Android based control system is presented in this paper where the proposed system can maintain the security of home main entrance and also the car door lock. Another important feature of the designed system is that it can control the overall appliances in a room. The mobile to security system or home automation system interface is established through Bluetooth. The hardware part is designed with the PIC microcontroller.
The World Wide Web is booming and radically vibrant due to the well established standards and widely accountable framework which guarantees the interoperability at various levels of the application and the society as a whole. So far, the web has been functioning at the random rate on the basis of the human intervention and some manual processing but the next generation web which the researchers called semantic web, edging for automatic processing and machine-level understanding. The well set notion, Semantic Web would be turn possible if only there exists the further levels of interoperability prevails among the applications and networks. In achieving this interoperability and greater functionality among the applications, the W3C standardization has already released the well defined standards such as RDF/RDF Schema and OWL. Using XML as a tool for semantic interoperability has not achieved anything effective and failed to bring the interconnection at the larger level. This leads to the further inclusion of inference layer at the top of the web architecture and its paves the way for proposing the common design for encoding the ontology representation languages in the data models such as RDF/RDFS. In this research article, we have given the clear implication of semantic web research roots and its ontological background process which may help to augment the sheer understanding of named entities in the web.
Wireless sensor networks provide ubiquitous computing systems in various open environments. In the
environment, sensor nodes can easily be compromised by adversaries to generate injecting false data
attacks. The injecting false data attack not only consumes unnecessary energy in en-route nodes, but also
causes false alarms at the base station. To detect this type of attack, a bandwidth-efficient cooperative
authentication (BECAN) scheme was proposed to achieve high filtering probability and high reliability
based on random graph characteristics and cooperative bit-compressed authentication techniques. This
scheme may waste energy resources in en-route nodes due to the fixed number of forwarding reports. In
this paper, our proposed method effectively selects a dynamic number of forwarding reports in the source
nodes based on an evaluation function. The experimental results indicate that our proposed method
enhances the energy savings while maintaining security levels as compared to BECAN.
Artificial neural networks (ANN) consider classification as one of the most dynamic research and
application areas. ANN is the branch of Artificial Intelligence (AI). The neural network was trained by
back propagation algorithm. The different combinations of functions and its effect while using ANN as a
classifier is studied and the correctness of these functions are analyzed for various kinds of datasets. The
back propagation neural network (BPNN) can be used as a highly successful tool for dataset classification
with suitable combination of training, learning and transfer functions. When the maximum likelihood
method was compared with backpropagation neural network method, the BPNN was more accurate than
maximum likelihood method. A high predictive ability with stable and well functioning BPNN is possible.
Multilayer feed-forward neural network algorithm is also used for classification. However BPNN proves to
be more effective than other classification algorithms.
Wireless sensor networks (WSNs) are regularly deployed in harsh and unattended environments, and
sensor nodes are easily exposed to attacks due to the random arrangement of the sensor field. An attacker
can inject fabricated reports from a compromised node with false votes and false vote-based reports. The
false report attacks can waste the energy of the intermediate nodes, shortening the network lifetime.
Furthermore, false votes cause the filtering out of legitimate reports. A probabilistic voting-based filtering
scheme (PVFS) was proposed as a countermeasure against this type of attacks by Li and Wu. PVFS uses a
vote threshold, a security threshold, and a verification node. The scheme does not make additional use
energy or communications resources because the verification node and threshold values are fixed. There
needs to be a verification node selection method that considers the energy resources of the node. In this
paper, we propose a verification path election scheme based on a fuzzy logic system. In the proposed
scheme, one node transmits reports in the node with a strong state through a fuzzy logic system after which
a neighbor is selected out of two from the surroundings. Experimental results show that the proposed
scheme improves energy savings up to maximum 13% relative to the PVFS.
In this paper a novel intelligent soft computing based cryptographic technique based on synchronization of
two chaotic systems (CSCT) between sender and receiver has been proposed to generate session key using
Pecora and Caroll (PC) method. Chaotic system has some unique features like sensitive to initial
conditions, topologically mixing; and dense periodic orbits. By nature, the Lorenz system is very sensitive
to initial conditions meaning that the error between attacker and receiver is going to grow exponentially if
there is a very slight difference between their initial conditions. All these features make chaotic system as
good alternatives for session key generation. In the proposed CSCT few parameters ( , b , r , x1 ,y2 and z2 )
are being exchanged between sender and receiver. Some of the parameter which takes major roles to form
the session key does not get transmitted via public channel, sender keeps these parameters secret. This way
of handling parameter passing mechanism prevents any kind of attacks during exchange of parameters like
sniffing, spoofing or phishing.
A black-hole attack in the Mobile Ad-hoc NETwork (MANET) is an attack occurs due to malicious nodes,
which attracts the data packets by falsely advertising a fresh route to the destination. In this paper, we
present a clustering approach in Ad-hoc On-demand Distance Vector (AODV) routing protocol for the
detection and prevention of black-hole attack in MANETs. In this approach every member of the cluster will
ping once to the cluster head, to detect the peculiar difference between the number of data packets received
and forwarded by the node. If anomalousness is perceived, all the nodes will obscure the malicious nodes
from the network.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesChristina Lin
Traditionally, dealing with real-time data pipelines has involved significant overhead, even for straightforward tasks like data transformation or masking. However, in this talk, we’ll venture into the dynamic realm of WebAssembly (WASM) and discover how it can revolutionize the creation of stateless streaming pipelines within a Kafka (Redpanda) broker. These pipelines are adept at managing low-latency, high-data-volume scenarios.
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...University of Maribor
Slides from talk presenting:
Aleš Zamuda: Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapter and Networking.
Presentation at IcETRAN 2024 session:
"Inter-Society Networking Panel GRSS/MTT-S/CIS
Panel Session: Promoting Connection and Cooperation"
IEEE Slovenia GRSS
IEEE Serbia and Montenegro MTT-S
IEEE Slovenia CIS
11TH INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONIC AND COMPUTING ENGINEERING
3-6 June 2024, Niš, Serbia
Literature Review Basics and Understanding Reference Management.pptxDr Ramhari Poudyal
Three-day training on academic research focuses on analytical tools at United Technical College, supported by the University Grant Commission, Nepal. 24-26 May 2024
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELgerogepatton
As digital technology becomes more deeply embedded in power systems, protecting the communication
networks of Smart Grids (SG) has emerged as a critical concern. Distributed Network Protocol 3 (DNP3)
represents a multi-tiered application layer protocol extensively utilized in Supervisory Control and Data
Acquisition (SCADA)-based smart grids to facilitate real-time data gathering and control functionalities.
Robust Intrusion Detection Systems (IDS) are necessary for early threat detection and mitigation because
of the interconnection of these networks, which makes them vulnerable to a variety of cyberattacks. To
solve this issue, this paper develops a hybrid Deep Learning (DL) model specifically designed for intrusion
detection in smart grids. The proposed approach is a combination of the Convolutional Neural Network
(CNN) and the Long-Short-Term Memory algorithms (LSTM). We employed a recent intrusion detection
dataset (DNP3), which focuses on unauthorized commands and Denial of Service (DoS) cyberattacks, to
train and test our model. The results of our experiments show that our CNN-LSTM method is much better
at finding smart grid intrusions than other deep learning algorithms used for classification. In addition,
our proposed approach improves accuracy, precision, recall, and F1 score, achieving a high detection
accuracy rate of 99.50%.
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
Comparative analysis between traditional aquaponics and reconstructed aquapon...bijceesjournal
The aquaponic system of planting is a method that does not require soil usage. It is a method that only needs water, fish, lava rocks (a substitute for soil), and plants. Aquaponic systems are sustainable and environmentally friendly. Its use not only helps to plant in small spaces but also helps reduce artificial chemical use and minimizes excess water use, as aquaponics consumes 90% less water than soil-based gardening. The study applied a descriptive and experimental design to assess and compare conventional and reconstructed aquaponic methods for reproducing tomatoes. The researchers created an observation checklist to determine the significant factors of the study. The study aims to determine the significant difference between traditional aquaponics and reconstructed aquaponics systems propagating tomatoes in terms of height, weight, girth, and number of fruits. The reconstructed aquaponics system’s higher growth yield results in a much more nourished crop than the traditional aquaponics system. It is superior in its number of fruits, height, weight, and girth measurement. Moreover, the reconstructed aquaponics system is proven to eliminate all the hindrances present in the traditional aquaponics system, which are overcrowding of fish, algae growth, pest problems, contaminated water, and dead fish.
A review on techniques and modelling methodologies used for checking electrom...nooriasukmaningtyas
The proper function of the integrated circuit (IC) in an inhibiting electromagnetic environment has always been a serious concern throughout the decades of revolution in the world of electronics, from disjunct devices to today’s integrated circuit technology, where billions of transistors are combined on a single chip. The automotive industry and smart vehicles in particular, are confronting design issues such as being prone to electromagnetic interference (EMI). Electronic control devices calculate incorrect outputs because of EMI and sensors give misleading values which can prove fatal in case of automotives. In this paper, the authors have non exhaustively tried to review research work concerned with the investigation of EMI in ICs and prediction of this EMI using various modelling methodologies and measurement setups.
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
A CONCEPTUAL FRAMEWORK OF A DETECTIVE MODEL FOR SOCIAL BOT CLASSIFICATION
1. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
DOI : 10.5121/ijasa.2022.10402 9
A CONCEPTUAL FRAMEWORK OF A DETECTIVE
MODEL FOR SOCIAL BOT CLASSIFICATION
Emmanuel Etuh1,2
, George E. Okereke1
, Deborah U. Ebem1
,
and Francis S. Bakpo1
1
Department of Computer Science, Faculty of Physical Sciences,
University of Nigeria Nsukka, Nigeria
2
Department of Mathematics/Statistics/Computer Science,
Kwararafa University, Wukari, Taraba State, Nigeria
ABSTRACT
Social media platform has greatly enhanced human interactive activities in the virtual community. Virtual
socialization has positively influenced social bonding among social media users irrespective of one’s
location in the connected global village. Human user and social bot user are the two types of social media
users. While human users personally operate their social media accounts, social bot users are developed
software that manages a social media account for the human user called the botmaster. This botmaster in
most cases are hackers with bad intention of attacking social media users through various attacking mode
using social bots. The aim of this research work is to design an intelligent framework that will prevent
attacks through social bots on social media network platforms.
KEYWORDS
Social media platform, human user, social bot, hackers, social security, intrusion prevention
1. INTRODUCTION
Virtual socialization has greatly enhanced social bonding irrespective of one‟s location in the
global village. Different social media platform exists to help with different aspects of social
interactions. During the past decade, social media like Twitter and Facebook emerged as a
widespread tool for massive-scale and real-time communication [1]. Twitter and Facebook alone
attracts over 500 million users across the world [2] which shows a rapid growth in the virtual
community. Two categories of social media users identified in this virtual community are human
users and social bot users. While human users personally operate their social media accounts,
social bot users are developed software that manages a social media account for the human user
called the botmaster. A typical example of a social bot user is a twitter bot which can be
automated to write tweets, re-tweet, and like a tweet. Twitter platform does not mind the use of
Twitter bot accounts as long as they do not break the Terms of Service of the platform [3]. Just as
there are good human social media users and bad users called hackers, there are also good social
bot user that manages the botmaster‟s account and bad ones as well used for attacks on the social
media platform. Majority of human users of the social media platform are less knowledgeable
about the functionality, security features and precautionary measures necessary to enhance safe
interaction in the social cyberspace. In a more convenient way, bad users called hackers
preferably employ the use of bad social bots to attack unsuspecting users. Hence, differentiating
between a human user and bad social bot user becomes essential to inform a naïve user on the
level of trust to be given to a social connection for virtual interaction. There is a need for a more
reassuring proof of identity in the global village [4]–[7]. This proof of identity verification can
2. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
10
either be through what the user does on the social media platform (user activities) or account
features of the user. Varying attacks have been witnessed on the social media platform, these
attacks have been summarized in [8].
Many researchers have proposed different security mechanisms to curtail the activities of hackers
on social media platform. Some of these proposals include: biometric authentication, hybrid
system for anomaly detection in social networks [9], Network Intrusion Detection System [10],
[11], [12]. On social bot detection, [13] proposed “An Evolutionary Computation Approach for
Twitter Bot Detection”, [14] worked on “Twitter bot detection using supervised machine
learning”, [15] worked on “Twitter Bot Detection using Diversity Measures”, [16] proposed
“Twitter Bot Detection Using Bidirectional Long Short-term Memory Neural Networks and
Word Embeddings”, [3] proposed “Supervised Machine Learning Bot Detection Techniques to
Identify Social Twitter Bots”, [1] proposed “Deep Neural Networks for Bot Detection”, [2]
proposed “Fake Account Detection in Twitter Based on Minimum Weighted Feature set.
Being an evolving domain that is rapidly growing, different proposal for social bot detection on
social media platform is still evolving. Hackers too are not relenting in developing evading
techniques to detection. Hence, there is therefore a need for intelligent intrusion detection (IIDM)
model that is efficient to disarm the hackers from carrying out their cybercrime activities against
SMNP by promptly notifying a typical social media human user the account category of a new
found user on the platform to prevent attacks through social bot developed by hackers for
malicious intention. This work seeks to enhance the social media usage by exposing hackers‟ use
of social bots which are potential wide scale attacking tool on the social media platform.
2. RELATED LITERATURES
Due to the virtual nature of the global village occasioned by the advent of the Internet [5], human
users and social bot users interact in the virtual world. This mixed interaction affects virtual
socialization. In this section, a theoretical background is given on social media platform and the
proposed model by some researcher on how to counter attacks on the social media platform.
2.1. Theoretical Background
Social media platforms have become an integral part of average Internet users in the virtual
community today. Billions of connected devices to the Internet operate on one social media
platform or the other. According to report in [17], over 500 million IoT devices were
implemented globally in 2003, 12.5 billion in 2010, and 50 billion in 2020. There are about 3.5
billion people on social media with an estimated attacks that generate over $3 billion annually for
cyber criminals [18]. Online social network platform like Facebook incorporate several
functionalities which includes product and services advertisement, and sales that makes it
relevant to almost all internet users either cooperate or private. The Covid19 pandemic has been
instrumental to the geometric shift to virtual socialization. Also, the technological shift to cloud
computing paradigm also has positively influenced the ubiquity of social media. This has also
increased cybercriminals‟ activity on the platform. According to a survey by CERT, the rate of
cyber-attacks has been doubling every year [10]. Online social network is faced with threatening
security challenges [19]. This shift seems to have given hacker an edge to securely carryout their
nefarious acts since humans are less involved. Cloud intrusion attacks are set of actions that
attempt to violate the integrity, confidentiality or availability of cloud resources on cloud SMNP.
The rising drop in processing and Internet accessibility cost is also increasing users‟ vulnerability
to a wide variety of cyber threats and attacks. There are two types of users of social media
platforms, they are: human users and social bot users. The human users are human beings that
3. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
11
directly operate their social media account through connected devices while social bot users are
developed software that manages a social account for a human user. These social bot users can
also be categorized into two depending on the activities carried out by them to be either good
social bot or bad social bot [2]. The bad social bot are malicious software designed for misuse of
a targeted social media platform. Intrusion detection is meant to detect misuse or an unauthorized
use of the computer systems by internal and external elements [11]. IDS are an effective security
technology, which can detect, prevent and possibly react to the attack [20], [21] opined that
artificial Intelligence plays a driving role in security services like intrusion detection. Several
attacks on social media platforms can best be detected by developing an intelligent intrusion
detection model for social media platform [8].
2.2. Review of Related Literatures
[13] proposed “An Evolutionary Computation Approach for Twitter Bot Detection”. The
researcher used genetic algorithms and genetic programming to discover interpretable
classification models for Twitter bot detection with competitive qualitative performance, high
scalability, and good generalization capabilities. The model was able to detect twitter bots with
detection accuracy of 75 per cent.
[14] proposed “Twitter bot detection using supervised machine learning“. They used algorithms
like Decision tree, K nearest neighbours, Logistic regression, and Naïve Bayes to calculate
accuracy in classifying bots and compared it with their model classifier that used bag of bots‟
word model to detect Twitter bots from a given training data set. The proposed classifier is based
on Bag of Words (BoW) model which is used to extract features from text in the areas of Natural
Language Processing or NLP, Computer Vision and Information Retrieval (IR). The twits from a
user is compared with BoW to determine if the account is a bot.
[2] proposed “Fake Account Detection in Twitter Based on Minimum Weighted Feature set”.
Over 22 factors for determining a fake account were mined out of which the study minimized set
of the main factors that influence the detection of the fake accounts on Twitter, and then the
determined factors are applied using different classification techniques.
[16] proposed “Twitter Bot Detection Using Bidirectional Long Short-term Memory Neural
Networks and Word Embeddings” the model used Bidirectional Long Short-term Memory
Neural Networks and Word Embeddings for Twitter bot detection. The model only relies
on tweets and does not require heavy feature engineering to detect bots on Twitter.
[1] proposed a “Deep Neural Networks for Bot Detection”. Their model design was based on
contextual long short-term memory (LSTM) architecture that exploits both content and metadata
to detect bots at the tweet level. Other contextual features are extracted from user metadata and
fed as auxiliary input to LSTM deep nets processing the tweet text forming a dens layer that
generate the output which classifies the accounts as either bot or not.
[9] proposed “an efficient hybrid system for anomaly detection in social networks”. The model
cascaded several machine learning algorithms that included decision tree, Support Vector
Machine (SVM) and Naïve Bayesian classifier (NBC) for classifying normal and abnormal users
on social networks. the anomaly detection engine uses SVM algorithm to classify social media
network user as happy or disappointed, NBC algorithm is used based on a defined dictionary to
classify social media users with social tendency. Unique features derived from users‟ profile and
contents were extracted and used for training and testing of the model, performance evaluation
conducted by experiment on the model using synthetic and real datasets from social network
shows 98% accuracy.
4. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
12
[3] proposed “Supervised Machine Learning Bot Detection Techniques to Identify Social Twitter
Bots”. The model combined user profile, account activity, and text mining to predict the user
account as bot or otherwise using complex machine learning algorithm which utilized a range of
features like length of user names, reposting rate, temporal patterns, sentiment expression,
followers-to-friends ratio, and message variability for bot detection
3. CONCEPTUAL FRAMEWORK
The proposed Intelligent Intrusion Detection Model for social bot classification will follow
Machine Learning (ML) design approach. Machine learning is all about programming computers
to optimize a performance criterion using past experience encoded as dataset [22]. A social media
user on a particular platform can verify each social contact to detect the status of the account
which should influence the extent of virtual socialization with the new user. The proposed system
will utilize account-level features to identify „who the user is‟ in the virtual space. If an account is
detected to be a social bot, the user is notified. This will serve as a preventive mechanism that
will shield the user from the designed attacks of the hacker that uses bots to attack the social
media user. Otherwise, if the account is detected to be a human user, then the social media user
can now virtually relate with the user. Beforehand, the social media user would have fallen into
this kind of attack before devising a way of recovering from the attack, but with the proposed
model, the user will escape social bot related attacks.
3.1. Activity Diagram
The user, the model, and the platform are the three entities to be considered in the proposed
design. The social media user triggers the activity when they want to connect with a new user.
This activity triggers the model to extract the account features of the new social media user to
identify the type of user it is. A web crawler will be used to extract the account features of the
new user, this feature dataset will be passed to the model for detection, if the prediction of the
new user is a bot, the details will be communicated to the user in a log file and the activity stops.
Else, the user can now read new twits from the new user or follow the new user or interact
socially with the new user without fear of attack. The activity diagram of the model is presented
in Fig 1 below.
5. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
13
Fig 1: Activity Diagram
3.2. Flow chart
The model read the new user and extracts the user features that will be passed to the detection
engine to predict if the new user is a social bot or a human being to enable the typical user make
informed decision on how to relate with the user. If the model predicts the user to be a human
user, the typical user can then go on to virtually relate with the user. The flowchart of the
proposed model is presented in Fig 2
6. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
14
Fig 2: Flow chart
3.3. Conceptual Framework
The intrusion prevention model interfaces between the new user, the social media platform and
the human user. Before any social interaction in the virtual space, the human user is expeted to
verify the new user to ensure they are not bad bots. To do this, the prevention model can be used
to check the status of the new user to identify the class of user it belong. This is achieved using
the detection model. Firstly, the web crawler extract the new user account features from the social
media platform. This feature dataset will be passed to the detection engine for processing. The
output of the processing is user classification as either social bot or human user depending on the
threshold assertained by the detection engine. A notification message is communicated to the user
to enable the user to determine the level of trust to accord to the new user.
The high level view of the proposed system is presented in figure 4. The social media user
triggers a request either POST or GET request to the social media server, the request handler
which is the social media platform crawler generate a dataset of account-level features of the user
which is passed to the detection layer for analysis and categorization. If the percentage of the
likelihood of the account falls below the defined threshold, the user is classified as a social bot,
else, the user is classified as a normal human user. The communication of the message is passed
to the user through the API for decision making by the social media user that wants to initiate
connection with the new user.
7. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
15
Fig 3: Conceptual model
3.4. Performance Measurement
To evaluate the performance of the model, four standard indicators will be used to evaluate the
performance of the model. Machine learning models according to [23] has standard performance
indicators for measuring its performance. They are: True Negative (TN), True Positive (TP),
False Negative (FN), and False Positive (FP).
i) True Positive (TP): is when the social media account is predicted to belong to a human
user or social bot class and it actually does belong to that class.
ii) False Positive (FP) is when the social media account is predicted to belong to a human
user or social bot class and it actually does not belong to that class.
iii) True Negative (TN) is when the social media account is predicted not to belong to a
human user or social bot class and it actually does not belong to that class.
iv) False Negative (FN) is when the social media account is predicted not to belong to a
human user or social bot class and it actually does belong to that class.
Other evaluation parameters are precision, accuracy, recall, and F1 score [23] [24][25]. The f-
score is used to weigh the overall performance of a developed machine learning model, accuracy
is the number of correctly predicted values out of the total prediction sample space.
Precision is the number of true predictions that were positive against the true positives with the
false positives. They are defined by equation (1) - (4).
8. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
16
4. CONCLUSIONS
The wide scale usage of social media that has attracted the activities of hackers must be securely
protected against the malicious activities of hackers that use bad social bot to attack naïve users.
Therefore an intelligent intrusion prevention system will greatly enhance the enormous benefits
available on the social media network platforms. The research work will design an intelligent
intrusion prevention framework that will prevent attacks through bad social bots on social media
network platforms. Several attacks which can be launched by hackers using bad social bots will
be proactively averted even before they connect virtually with any social media user.
ACKNOWLEDGEMENTS
The authors would like to thank the PG board of the department of Computer Science University
of Nigeria for their constructive criticism on this research work.
AUTHORS
Emmanuel Etuh is a lecturer in the department of Mathematics, Statistics, and
Computer Science at Kwararafa University, Wukari, Nigeria and currently pursuing a
PhD degree in Computer Science at the University of Nigeria, Nsukka. He obtained his
first degree certificate in Computer Science from Kogi State University, Anyigba in
2009 and an MSc degree in Computer Science from Ahmadu Bello University, Zaria in
2014, His research interests include Artificial Intelligence, Cyber Security, and Software
Engineering.
Okereke George Emeka is a senior Lecturer/Researcher, Computer Science
Department, University of Nigeria, Director, Computing Centre, Former Head of
Department, Computer Science, University of Nigeria. He obtained a Bachelor of
Engineering (Hons.) in Computer Science & Engineering from Enugu State University
of Science and Technology and a Master of Science degree in Computer science from
University of Nigeria. His PhD is in Digital Electronics & Computing from Electronic
Engineering Department of University of Nigeria. He joined the services of University
of Nigeria in 1998 as a lecturer in Computer Science Department and is currently a Senior Lecturer. Head
of Department from 2017 to 2019. His research interest is in Network security, web security, computer
forensics, electronic transfers and security, web design and computer architecture/design. George is
married with six children.
Dr. Ir. Engr. (Mrs.) Deborah Uzoamaka Ebem is a lecturer in the department of
Computer Science, University of Nigeria, Nsukka. Deborah is a native of Ugbo In
Awgu Local Government Area of Enugu State. She received a B.Engr. degree from
Anambra State University of Technology (ASUTECH) and a postgraduate diploma in
management from University of Nigeria, Nsukka. She also received master‟s degrees in
Computer Science and Engineering and Computer Engineering from Enugu State
9. International Journal of Ambient Systems and Applications (IJASA), Vol.10, No.4, December 2022
17
University of Science (ESUT) and the Technical University Delft, The Netherlands, respectively. She
further holds a PhD in Computer Science from Ebonyi State University, Abakaliki, Nigeria. She was a
Research Fellow and Scholar at Massachusetts Institute of Technology (MIT), Cambridge USA.
Bakpo Francis S is a Professor in the Department of Computer Science, University of
Nigeria, Nsukka. He joined the Department of Computer Science, University of Nigeria,
Nsukka as a Corp member in 1995, retained by the Department in 1996 as lecturer II and
progressed to Professor in 2010. He received his Master's degree in Computer Science
and Engineering from Kazakh National Technical University, Almaty (formerly, USSR)
in 1994 and Doctorate degree in Computer Engineering in 2008 from Enugu State
University of Science and Technology, Agbani. Area of Specialization include: computer architecture,
computer communications network, Artificial neural network, intelligent software agents and Petri nets
theory and applications.