Data Mining in Cyber Security Intrusion Detection
Presented by : Sagar Deepak Thapa
Guided By : Prof Nagaraju Bogiri
KJ College Of Engineering And Management Research Pune
4072
Outline
What is Cyber Security?
What is Cyber Crime?
Applications of Data Mining in Cyber Security.
Intrusion detection.
Why Can Data Mining Help?
Data Mining approaches for Intrusion Detection.
Conclusion.
Cyber Security
Set of technologies and processes designed to protect computers,
networks, programs, and data from attack, unauthorized access, change,
or destruction.
A Majorpart of Cyber Security
is to fix broken Software.
Cyber
Security
Computer
SecuritySystem
Network
SecuritySystem
Cyber Crime
Encompasses anycriminal act dealingwith computers and networks.
Include:
• Malicious programs.
• Illegal imports.
• Computers Vandalism.
Cyber Security VS CyberCrime
Cyber
Security
CyberCrime CyberSecurity
Cyber
Crime
One side of the
coin
Other side of the
coin
Applications of Data Mining in Cyber Security
Malwaredetection.
Intrusion detection.
Fraud detection.
Intrusion Detection
The process of monitoring the events occurring in a computer systemor
network and analyzing them for signs of intrusion.
Intrusion Detection System (IDS)
Combination of software and hardware that attempts to perform
intrusion detection.
Raise the alarm when possible intrusion happens.
Steps:
 Monitoring and analyzing traffic.
 Identifying abnormal activities.
 Assessing severity and raisingalarm.
Detector – ID Engine
Response
Component
Data gathering (sensors)
Raw data
Information Source - Monitored System
Events
Knowledge base Configuration
Alarms
Actions
SystemState
System
State
Intrusion Detection System Architecture
Goals of Intrusion Detection System (IDS)
Detect wide variety of intrusions.
Detect intrusions in timelyfashion.
Present analysis in simple, easy-to-understand format.
Be accurate.
WhyWeNeed Intrusion Detection?
Security mechanisms always have inevitable vulnerabilities.
Multiple levels of data confidentiality in commercial and government
organizations needs multi-layer protection in firewalls.
Why Can Data MiningHelp?
 Successful applications in related domains, e.g., fraud detection,
fault/alarm management.
 Learn from traffic data
 Maintain or update models on dynamic data.
 Data mining: applying specific algorithms to extract patterns from
data.
 From the data-centric point view
, intrusion detection is a data
analysisprocess.
Data Mining approaches for Intrusion Detection
Classification Methods
 Neural networks.
 Bayesian classification.
 Support vector
machines.
Email Worm Detection Using Data Mining
Outgoing Emails
TrainingData
TestData
Classifier
Feature
Extraction
Machine
Learning
Themodel
CleanorInfected
Clustering
Group data into clusters
ClusteringApproaches
• K-means
• Hierarchical Clustering
Clustering for Intrusion Detection
Anomaly detection.
Any significant deviations from the expected behavior are reported as
possible attacks.
Build clusters as models for normal activities.
Conclusion
Data mining has great potential as a malware detection tool. It allows you
to analyze huge sets of information and extract new knowledge from it.
The main benefit of using data mining techniques for detecting
malicious software is the ability to identify both known and zero-day
attacks.
THANK YOU

Data mining in Cyber security

  • 1.
    Data Mining inCyber Security Intrusion Detection Presented by : Sagar Deepak Thapa Guided By : Prof Nagaraju Bogiri KJ College Of Engineering And Management Research Pune 4072
  • 2.
    Outline What is CyberSecurity? What is Cyber Crime? Applications of Data Mining in Cyber Security. Intrusion detection. Why Can Data Mining Help? Data Mining approaches for Intrusion Detection. Conclusion.
  • 3.
    Cyber Security Set oftechnologies and processes designed to protect computers, networks, programs, and data from attack, unauthorized access, change, or destruction. A Majorpart of Cyber Security is to fix broken Software. Cyber Security Computer SecuritySystem Network SecuritySystem
  • 4.
    Cyber Crime Encompasses anycriminalact dealingwith computers and networks. Include: • Malicious programs. • Illegal imports. • Computers Vandalism.
  • 5.
    Cyber Security VSCyberCrime Cyber Security CyberCrime CyberSecurity Cyber Crime One side of the coin Other side of the coin
  • 6.
    Applications of DataMining in Cyber Security Malwaredetection. Intrusion detection. Fraud detection.
  • 7.
    Intrusion Detection The processof monitoring the events occurring in a computer systemor network and analyzing them for signs of intrusion.
  • 8.
    Intrusion Detection System(IDS) Combination of software and hardware that attempts to perform intrusion detection. Raise the alarm when possible intrusion happens. Steps:  Monitoring and analyzing traffic.  Identifying abnormal activities.  Assessing severity and raisingalarm.
  • 9.
    Detector – IDEngine Response Component Data gathering (sensors) Raw data Information Source - Monitored System Events Knowledge base Configuration Alarms Actions SystemState System State Intrusion Detection System Architecture
  • 10.
    Goals of IntrusionDetection System (IDS) Detect wide variety of intrusions. Detect intrusions in timelyfashion. Present analysis in simple, easy-to-understand format. Be accurate.
  • 11.
    WhyWeNeed Intrusion Detection? Securitymechanisms always have inevitable vulnerabilities. Multiple levels of data confidentiality in commercial and government organizations needs multi-layer protection in firewalls.
  • 12.
    Why Can DataMiningHelp?  Successful applications in related domains, e.g., fraud detection, fault/alarm management.  Learn from traffic data  Maintain or update models on dynamic data.  Data mining: applying specific algorithms to extract patterns from data.  From the data-centric point view , intrusion detection is a data analysisprocess.
  • 13.
    Data Mining approachesfor Intrusion Detection
  • 14.
    Classification Methods  Neuralnetworks.  Bayesian classification.  Support vector machines.
  • 15.
    Email Worm DetectionUsing Data Mining Outgoing Emails TrainingData TestData Classifier Feature Extraction Machine Learning Themodel CleanorInfected
  • 16.
    Clustering Group data intoclusters ClusteringApproaches • K-means • Hierarchical Clustering
  • 17.
    Clustering for IntrusionDetection Anomaly detection. Any significant deviations from the expected behavior are reported as possible attacks. Build clusters as models for normal activities.
  • 18.
    Conclusion Data mining hasgreat potential as a malware detection tool. It allows you to analyze huge sets of information and extract new knowledge from it. The main benefit of using data mining techniques for detecting malicious software is the ability to identify both known and zero-day attacks.
  • 19.