Inferring Speech Activity from Encrypted Skype Traffic

•

1 like•766 views

Normally, voice activity detection (VAD) refers to speech processing algorithms for detecting the presence or absence of human speech in segments of audio signals. In this paper, however, we focus on speech detection algorithms that take VoIP traffic instead of audio signals as input. We call this category of algorithms network-level VAD. Traditional VAD usually plays a fundamental role in speech processing systems because of its ability to delimit speech segments. Network-level VAD, on the other hand, can be quite helpful in network management, which is the motivation for our study. We propose the first real-time network-level VAD algorithm that can extract voice activity from encrypted and non-silence-suppressed Skype traffic. We evaluate the speech detection accuracy of the proposed algorithm with extensive reallife traces. The results show that our scheme achieve reasonably good performance even high degree of randomness has been injected into the network traffic.

Technology Business

Inferring Speech Activity from
Encrypted Skype Traffic

Yu‐Chun Chang, Kuan‐Ta Chen, Chen‐Chi Wu, and
Chin‐Laung Lei

Oct. 27, 2008

2008/10/27 1

Outline
• Introduction
• Data description
• Proposed scheme
• Performance evaluation
• Conclusion

2008/10/27 2

Introduction
• VAD (Voice Activity Detection)
– The algorithm to extract the presence or absence
of human speech in speech processing.
• Source‐level VAD
– Audio signal
– Silence suppression
• Network‐level VAD
– Network traffic
– Flow identification, QoS measurement
2008/10/27 3

• The differences between source‐level and network‐
level VAD

source‐level network‐level
input audio signal network traffic
location speaker’s host network node
purpose silence suppression traffic management
echo cancellation QoS measurement

2008/10/27 4

Introduction (contd.)
• Challenges
– Payload encryption
– Skype do not support silence suppression
• Contribution
– We propose a network‐level VAD that can infers
speech activity from encrypted and non‐silence‐
suppressed VoIP traffic.

2008/10/27 5

Data Description
• Experiment setup

(Chosen by Skype)

2008/10/27 Audio signal Network traffic 6

Data Description (contd.)
• Trace summary

Total # of traces # TCP # UDP
1839 1427 412

# Relay node Mean packet size Mean time period
1677 109.6 bytes 612.5 sec

2008/10/27 7

Proposed Scheme
• The indicator of voice activity – packet size
• Smoothing
• Adaptive thresholding

2008/10/27 8

The indicator of voice activity – Packet size

2008/10/27 9

Smoothing
• EWMA (Exponentially Weighted Moving Average)

EWMA :
Pi = λYi + (1 − λ ) Pi −1
(λ = 0.2)

Y : Observed packet size
P : Smoothed packet size
2008/10/27 10

Packet Size (bytes)
Adaptive thresholding

2008/10/27 11

Adaptive thresholding (contd.)
P : 140 bytes

(P + T2)/2 = 110 bytes
(P + T1)/2 = 107 bytes

T2 : 80 bytes
T1 : 74 bytes
2008/10/27 12

Adaptive thresholding (contd.)
Packet Size (bytes)

2008/10/27 estimated ON periods 13

Performance Evaluation
• Number of ON periods
Number _ of _ estimated _ ON _ periods
Number _ of _ true _ ON _ periods

2008/10/27 14

Performance Evaluation (contd.)
• Average length of ON periods
Mean _ length _ of _ estimated _ ON _ periods
Mean _ length _ of _ true _ ON _ periods

2008/10/27 15

Performance Evaluation (contd.)
• State correctness
M _ and _ N
ON period ‐> 1
M _ or _ N OFF period ‐> 0

True speech activity (M) : 0 0 1 1 1 0 0 0 1 1 0 1 1 0 0 0 0 0 1 1 1 1 1 0
Estimated speech activity (N): 0 1 1 1 1 0 0 0 1 0 0 1 1 0 0 0 0 1 1 1 0 1 1 1

M and N: 0 0 1 1 1 0 0 0 1 0 0 1 1 0 0 0 0 0 1 1 0 1 1 0
M or N: 0 1 1 1 1 0 0 0 1 1 0 1 1 0 0 0 0 1 1 1 1 1 1 1

2008/10/27 16

Performance Evaluation (contd.)
• State correctness

2008/10/27 17

Conclusion
• We propose the network‐level VAD which
infers speech activity from network traffic
instead of audio signal.
• We propose a VAD algorithm that can extract
voice activity from encrypted and non‐silence‐
suppressed VoIP network traffic.

2008/10/27 18

VAD on audio signaling

volume = 10 * log(∑ Si2 )
i

Static threshold : 183 db

J.‐S. R. Jang, “Audio signal processing and recognition,”
http://www.cs.nthu.edu.tw/jang
2008/10/27 21

I am a student of National Taiwan University.

2008/10/27 23

Performance Evaluation (contd.)
• Number of ON periods

2008/10/27 24

Performance Evaluation (contd.)
• Average length of ON periods

2008/10/27 25

Performance Evaluation (contd.)
• State correctness
M ∩N
M ∪N

True speech activity (M) : 0 0 1 1 1 0 0 0 1 1 0 1 1 0 0 0 0 0 1 1 1 1 1 0
Estimated speech activity (N): 0 1 1 1 1 0 0 0 1 0 0 1 1 0 0 0 0 1 1 1 0 1 1 1

2008/10/27 26

This document discusses inferring and provides examples of how to practice inferring from text. It begins with learning intentions and success criteria about inferring, which is constructing meaning beyond what is literally stated by using context clues and background knowledge. An activity is described where students listen to an audio clip and use inferring to predict what it is about. Another activity has students read newspaper articles without headlines and use inferring to predict the original headlines. The document emphasizes that inferring helps readers expand their understanding of what is implied but not explicitly stated.

Analyzing and inferring plot and theme

melzoerhof

This document discusses the difference between plot and theme in stories and how readers can infer themes. It explains that plot is made up of the sequence of events in a story, while theme represents deeper ideas that are suggested through textual clues but not directly stated. Readers can analyze both the plot and themes of their class novel by noticing details from the text, using background knowledge, and making inferences. The document provides examples of a plot point and potential theme from the story "Frog and Toad" and instructs students to respond to questions analyzing the plot and possible themes in their own class novel.

554 paper bag princess

lizbrianne

1) Inference is drawing a conclusion or judgment about something without directly observing it based on known information. 2) The document describes methods for teaching students to make inferences while reading, such as having them infer what a book is about from its cover, discussing inferences after reading, and having students practice making inferences in their own reading. 3) Research shows that explicitly teaching comprehension strategies like making inferences can improve students' general reading comprehension.

The thesis statement

melzoerhof

The document provides writing prompts and instructions for students to warm up and brainstorm ideas about a class novel. Students are encouraged to freely write claims and theses, then refine their ideas by underlining main points, rewriting thesis statements in different ways, and selecting the statement that feels most true and interesting to explore further. The next class will use today's brainstorming to construct a literary essay.

CGI_Multiplication_And_Division

Christiana Challoner

1) The document discusses Cognitively Guided Instruction (CGI), which uses students' intuitive understanding of math concepts as the basis for instruction. Research shows students intuitively understand the structures of multiplication, division, and word problems and can solve them using strategies like repeated addition or subtraction. 2) The three basic problem types for multiplication and division are identified based on which quantities (total objects, number of groups, objects in each group) are known/unknown. Students' strategies depend on discerning these structures. 3) A clinical interview with a student showed he relied on known math facts to solve most problems quickly. For problems requiring modeling, his reasoning was sometimes flawed. Developing multiple strategies could help him better

Inferring: The Heartbeat of Comprehension K-6

katiekeier

7 inferring

guest8cc62c

The document provides an overview of the concepts of observation and inference in scientific reasoning. It defines observation as an experience perceived through the senses, while an inference is an interpretation or explanation of an observation based on past experiences. It gives examples to illustrate observations and inferences. The document also outlines steps for making inferences, including making multiple observations, recalling relevant prior knowledge, and stating inferences in a way that distinguishes them from observations or predictions. It includes activities where the reader makes observations and inferences about objects and a set of animal tracks in snow.

Black Box Methods for Inferring Parallel Applications' Properties in Virtual ...

Ashish Gupta

The document discusses inferring properties of parallel applications running in virtual environments using black box methods. It presents an approach to infer communication behavior and runtime topology without any application-specific assumptions. Metrics like round trip iteration rate are introduced to measure performance in a black box way. Methods are also described to predict an application's slowdown under load and to estimate processing delays using analysis of inter-packet times in network traces.

This document analyzes and simulates channel switching for mobile live multi-channel TV streaming. It discusses the challenges of multi-channel access and channel switching delays. It proposes enhancing the user experience through analysis and design of server, client, and encoder subsystems, as well as configuring the system and simulating and testing it. Decreasing channel switching delay through optimizing chunk size and implementing fast channel switching can minimize protocol delay and maximize user experience.

Jawdat NGN IDNOG v1.0 public

Himawan Nugroho

This document appears to be a presentation on next generation networks and related topics. It includes sections on network architectures including passive optical networks and Ethernet, quality of service, MPLS VPNs, IPTV delivery, and network resiliency. Slides also address topics such as classification and marking for QoS, evolving business requirements, and differences between uniform and shortest path routing.

03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho

Indonesia Network Operators Group

JAWDAT NGN IDNOG v1.0 (public)[COPY]

Mahadiputra S

[Nov./2010] Adaptive Video Streaming over Wireless LAN with ns-2

Hayoung Yoon

P9 addressing signal_integrity_ in_ew_2015_final

Aamir Habib

This document discusses addressing signal integrity challenges in radar and electronic warfare systems due to increasing data bus rates. It describes how high speeds can lead to signal degradation through various effects. Measurement and characterization tools are needed to help designers avoid problems and ensure signals are transmitted and received correctly. Simulation and testing of high-speed digital designs is important from early stages of development through compliance testing.

Skype Video Responsiveness

soohyunc

This document discusses an experimental study of Skype video responsiveness to bandwidth variations. It aims to investigate how Skype adapts its video bitrate based on available bandwidth changes. The experiments show that Skype is elastic between 40-450kbps and can adapt to bandwidth steps and staircases, but with large transient times of over 100 seconds. Skype varies frame rate, resolution, and packet size to control rate. It also employs FEC to increase rate when losses are detected, making it more aggressive than TCP. The analysis provides insights into Skype's congestion control behavior.

Detecting VoIP Traffic Based on Human Conversation Patterns

Academia Sinica

Owing to the enormous growth of VoIP applications, an effective means of identifying VoIP is now essential for managing a number of network traffic issues, such as reserving bandwidth for VoIP traffic, assigning high priority for VoIP flows, or blocking VoIP calls to certain destinations. Because the protocols, port numbers, and codecs used by VoIP services are shifting toward proprietary, encrypted, and dynamic methods, traditional VoIP identification approaches, including port- and payload-based schemes, are now less effective. Developing a traffic identification scheme that can work for general VoIP flows is therefore of paramount importance. In this paper, we propose a VoIP flow identification scheme based on the unique interaction pattern of human conversations. Our scheme is particularly useful for two reasons: 1) flow detection relies on human conversations rather than packet timing; thus, it is resistant to network variability; and 2) detection is based on a short sequence of voice activities rather than the whole packet stream. Hence, the scheme can operate as a traffic management module to provide QoS guarantees or block VoIP calls in real time. The performance evaluation, which is based on extensive real-life traffic traces, shows that the proposed method achieves an identification accuracy of 95% in the first 4 seconds of the detection period and 97% in 11 seconds.

DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch

Jim St. Leger

2Fonet GEPON Presentation

ScorpAL

This document discusses GEPON (Gigabit Ethernet Passive Optical Networks), a fiber access technology for point-to-multipoint broadband access. It provides an overview of GEPON components including OLT, ONU, POS, and ODN. GEPON uses single fiber WDM with downlink at 1490nm and uplink at 1310nm, and can provide up to 1Gbps symmetrical bandwidth over distances up to 20km. The advantages of GEPON include high speeds, long transmission lengths, supporting data/voice/video, low maintenance requirements, and compatibility with Ethernet standards. The document also describes 2Fonet's GEPON products including the OLT3000 which can connect to

An Empirical Evaluation of VoIP Playout Buffer Dimensioning in Skype, Google ...

Academia Sinica

VoIP playout buffer dimensioning has long been a challeng- ing optimization problem, as the buffer size must maintain a balance between conversational interactivity and speech quality. The conversational quality may be affected by a number of factors, some of which may change over time. Although a great deal of research effort has been expended in trying to solve the problem, how the research results are applied in practice is unclear. In this paper, we investigate the playout buffer dimensioning algorithms applied in three popular VoIP applications, namely, Skype, Google Talk, and MSN Messenger. We conduct experiments to assess how the applications adjust their playout buffer sizes. Using an objective QoE (Quality of Experience) metric, we show that Google Talk and MSN Messenger do not adjust their respective buffer sizes appropriately, while Skype does not adjust its buffer at all. In other words, they could provide better QoE to users by improving their buffer dimensioning algorithms. Moreover, none of the applications adapts its buffer size to the network loss rate, which should also be considered to ensure optimal QoE provisioning.

Lagopus presentation on 14th Annual ON*VECTOR International Photonics Workshop

Lagopus SDN/OpenFlow switch

This document summarizes a presentation about Lagopus, an SDN software switch developed by NTT. Some key points: - Lagopus aims to provide an SDN-aware switch software stack capable of 100Gbps performance, including an OpenFlow agent and extensible configuration data store. - Existing virtual switches do not provide sufficient performance for carrier networks. Lagopus takes a simplified, modular design compiled using DPDK for high-performance packet processing. - An FPGA-based 40GbE NIC was developed to offload processing tasks like encryption and packet scheduling for improved performance. - Evaluation shows Lagopus can achieve wire-rate throughput of 10Gbps and support over 1 million flow

00868 sg brief-intro-to-information-theory

punithkumar M B

This document discusses channel coding and its implementation in wireless systems. It begins with an overview of information theory concepts like channel capacity for Gaussian and Rayleigh fading channels. It then compares the capacity of these channels. The document describes how the same data rate can be achieved using uncoded modulation or a coded modulation scheme with a convolutional code. It provides details on convolutional encoding and decoding using the Viterbi algorithm. Finally, it discusses a hardware implementation of a Viterbi decoder using an FPGA and concludes that channel coding can improve spectrum efficiency.

Core lab intro

Dimitris Katsaros

The document describes the Core Network Technologies Lab at OTEresearch which tests and evaluates core network technologies to support OTE's network planning, including testing broadband network gateways, IPv6, metro Ethernet, next generation SDH, and participating in research projects. In 2012, the lab successfully completed tests of major network upgrades and new equipment from various vendors. Key challenges for 2013 include expanding test beds and capabilities to keep up with network demands and growth.

Audio video ethernet (avb cobra net dante)

Jeff Green

AVB fits low-cost, small-form-factor products such as this microphone. The overall trend is that music no longer lives on shelves or in CD racks, but in hard drives in home computers, and increasingly in the cloud. This brings about its own unique problems, not in the encoding system used, or the storage technology, but in distributing the audio from the storage media to the speakers. AVB features are all enabled by a global and port level configuration. Connecting these elements is the AVB-enabled switch (in the graphic above, the Extreme Networks® Summit® X440.) The role of the switch is to provide support for the control protocols: AVB is Ethernet’s next stage of convergence, delivering pitch perfect audio and crystal clear video seamlessly over the network IP/Ethernet is bringing simplicity and features to audio and video as it has brought to services like VoIP, Storage and many more High quality, perfectly synchronized A/V until now has been difficult to maintain Standards work by the IEEE and the AVB standard changes everything, creating interoperability and mass-marketing equipment pricing Benefits of AVB - Delivers predictable latency and precise synchronization, maximizing the functionality of AV – time synchronization and quality or service Reduced complexity and Ease of use through interoperability between devices Streamlines complex network set-up and management, the Infrastructure negotiates and manages the network for optimal prioritized media transport AV traffic can co-exist with non-AV traffic on same Ethernet infrastructure Role based control at the XYZ Account - XYZ Account can identify devices and apply policies based on device type all the way down to the port and or the AP. Policies can dynamically change based on the device a user is connecting with and where that user is located. Extreme Networks provides infrastructure to deliver customizable prioritization and scalable capacity via configurable and built-in intelligence, ensuring a comprehensive, superior quality experience. Furthermore, when deployed with Extreme Wireless XYZ Account can configure the network to ensure applications receive the bandwidth they require, while still limiting or preventing high speed streaming of music of video or even games.

UDT

lilyco

The document describes the design and implementation of a new high performance data transport protocol called UDT. UDT is implemented at the application layer over UDP to provide reliable, high-speed data transfer capabilities. It includes a new congestion control algorithm based on AIMD with decreasing increases that aims for efficiency, fairness and friendliness. Experimental results show UDT achieves high throughput and good fairness compared to TCP. The document also introduces a configurable framework called Composable UDT that allows new congestion control algorithms to be easily implemented and evaluated.

Online learning for low-latency streaming

Theo Karagkioules

Learn2Adapt-LowLatency (L2A-LL) is a novel bitrate adaptation algorithm based on online learning that facilitates low-latency adaptive streaming. It does not require assumptions about network conditions and can generalize to different scenarios. L2A-LL optimizes video quality while maintaining a stable buffer and continuous streaming through a probabilistic decision process. It has been implemented in dash.js and shown to achieve high bitrates and low latency across different network profiles in preliminary experiments.

Itu ngn-v2

Luis Enrique Conde del Oso

The document discusses quality of experience (QoE) evaluation for next generation networks starting from ITU recommendations. It describes the background of telecom carriers moving to new IP/MPLS networks due to the obsolescence of TDM technology. Metrics and tools like FreeProbe are presented for validating QoE by analyzing video and audio quality over IP networks, along with test results from an IPTV service testing model that show the impact of packet loss and delay on subjective quality ratings.

Quantifying Skype User Satisfaction

Academia Sinica

The success of Skype has inspired a generation of peer-to-peer-based solutions for satisfactory real-time multimedia services over the Internet. However, fundamental questions, such as whether VoIP services like Skype are good enough in terms of user satisfaction, have not been formally addressed. One of the major challenges lies in the lack of an easily accessible and objective index to quantify the degree of user satisfaction. In this work, we propose a model, geared to Skype, but generalizable to other VoIP services, to quantify VoIP user satisfaction based on a rigorous analysis of the call duration from actual Skype traces. The User Satisfaction Index (USI) derived from the model is unique in that 1) it is composed by objective source- and network-level metrics, such as the bit rate, bit rate jitter, and round-trip time, 2) unlike speech quality measures based on voice signals, such as the PESQ model standardized by ITU-T, the metrics are easily accessible and computable for real-time adaptation, and 3) the model development only requires network measurements, i.e., no user surveys or voice signals are necessary. Our model is validated by an independent set of metrics that quantifies the degree of user interaction from the actual traces.

Rapid Detection of Constant-Packet-Rate Flows

Academia Sinica

The demand for effective VoIP and online gaming traffic management methods continues to increase for purposes such as QoS provisioning, usage accounting, and blocking VoIP calls or game connections. However, identifying such flows has become a significant administrative burden because many of the applications use proprietary signaling and transport protocols. The question of how to identify proprietary VoIP traffic has yet to be solved. In this paper, we propose using a deviation-based classifier to identify VoIP and gaming traffic, given that such real-time interactive services normally send out constant-packet-rate (CPR) traffic with a fixed interval, in order to maintain real-timeliness and interactivity. Our contribution is two-fold: 1) We show that scale-free variability measures are more appropriate than scaledependent ones for quantifying the network variability injected into CPR traffic. 2) Our proposed classifier is particularly lightweight in that it only requires a few inter-packet times to make a decision. The evaluation results show that by only analyzing 10 successive inter-packet times, we can distinguishbetween CPR and non-CPR traffic with approximately 90% accuracy.

Computational Social Science:The Collaborative Futures of Big Data, Computer ...

Academia Sinica

Games on Demand: Are We There Yet?

Academia Sinica

Games on demand, a.k.a., cloud gaming, refers to a new way to deliver computer games to users, where computationally complex games are executed and rendered on powerful cloud servers rather than local computing devices. In this talk, I will give an overview of the challenges in developing cloud gaming systems, what we have done, and what remains to do. I will start from GamingAnywhere, an open-source cloud gaming system, followed by a number of studies based on the system. Finally I will conclude the talk with open issues in providing highly real-time and high-definition audio/visual quality multimedia experience (e.g., in the form of gaming and virtual reality).

Similar to Inferring Speech Activity from Encrypted Skype Traffic

Bachelor Thesis Presentation: Analysis and Simulation Of Channel Switching In...

Laili Aidi

Jawdat NGN IDNOG v1.0 public

Himawan Nugroho

03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho

Indonesia Network Operators Group

JAWDAT NGN IDNOG v1.0 (public)[COPY]

Mahadiputra S

[Nov./2010] Adaptive Video Streaming over Wireless LAN with ns-2

Hayoung Yoon

P9 addressing signal_integrity_ in_ew_2015_final

Aamir Habib

Skype Video Responsiveness

soohyunc

Detecting VoIP Traffic Based on Human Conversation Patterns

Academia Sinica

DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch

Jim St. Leger

2Fonet GEPON Presentation

ScorpAL

An Empirical Evaluation of VoIP Playout Buffer Dimensioning in Skype, Google ...

Academia Sinica

Lagopus presentation on 14th Annual ON*VECTOR International Photonics Workshop

Lagopus SDN/OpenFlow switch

00868 sg brief-intro-to-information-theory

punithkumar M B

Core lab intro

Dimitris Katsaros

Audio video ethernet (avb cobra net dante)

Jeff Green

UDT

lilyco

Online learning for low-latency streaming

Theo Karagkioules

Itu ngn-v2

Luis Enrique Conde del Oso

Quantifying Skype User Satisfaction

Academia Sinica

Rapid Detection of Constant-Packet-Rate Flows

Academia Sinica

Similar to Inferring Speech Activity from Encrypted Skype Traffic (20)

Bachelor Thesis Presentation: Analysis and Simulation Of Channel Switching In...

Jawdat NGN IDNOG v1.0 public

03 (IDNOG01) NGN Next Generation Networks by Himawan Nugroho

JAWDAT NGN IDNOG v1.0 (public)[COPY]

[Nov./2010] Adaptive Video Streaming over Wireless LAN with ns-2

P9 addressing signal_integrity_ in_ew_2015_final

Skype Video Responsiveness

Detecting VoIP Traffic Based on Human Conversation Patterns

DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch

2Fonet GEPON Presentation

An Empirical Evaluation of VoIP Playout Buffer Dimensioning in Skype, Google ...

Lagopus presentation on 14th Annual ON*VECTOR International Photonics Workshop

00868 sg brief-intro-to-information-theory

Core lab intro

Audio video ethernet (avb cobra net dante)

UDT

Online learning for low-latency streaming

Itu ngn-v2

Quantifying Skype User Satisfaction

Rapid Detection of Constant-Packet-Rate Flows

More from Academia Sinica

Computational Social Science:The Collaborative Futures of Big Data, Computer ...

Academia Sinica

Games on Demand: Are We There Yet?

Academia Sinica

Detecting In-Situ Identity Fraud on Social Network Services: A Case Study on ...

Academia Sinica

In this paper, we propose to use a continuous authentication approach to detect the in-situ identity fraud incidents, which occur when the attackers use the same devices and IP addresses as the victims. Using Facebook as a case study, we show that it is possible to detect such incidents by analyzing SNS users’ browsing behavior. Our experiment results demonstrate that the approach can achieve reasonable accuracy given a few minutes of observation time.

Cloud Gaming Onward: Research Opportunities and Outlook

Academia Sinica

Cloud gaming has become increasingly more popular in the academia and the industry, evident by the large numbers of related research papers and startup companies. Some public cloud gaming services have attracted hundreds of thousands subscribers, demonstrating the initial success of cloud gaming services. Pushing the cloud gaming services forward, however, faces various challenges, which open up many research opportunities. In this paper, we share our views on the future cloud gaming research, and point out several research problems spanning over a wide spectrum of different directions: including distributed systems, video codecs, virtualization, human-computer interaction, quality of experience, resource allocation, and dynamic adaptation. Solving these research problems will allow service providers to offer high-quality cloud gaming services yet remain profitable, which in turn results in even more successful cloud gaming eco-environment. In addition, we believe there will be many more novel ideas to capitalize the abundant and elastic cloud resources for better gaming experience, and we will see these ideas and associated challenges in the years to come.

Quantifying User Satisfaction in Mobile Cloud Games

Academia Sinica

We conduct real experiments to quantify user satisfaction in mobile cloud games using a real cloud gaming system built on the open-sourced GamingAnywhere. We share our experiences in porting GamingAnywhere client to Android OS and perform extensive experiments on both the mobile and desktop clients. The experiment results reveal several new insights: (1) gamers are more satisfied with the graphics quality on mobile devices, while they are more satisfied with the control quality on desktops, (2) the bitrate, frame rate, and network delay significantly affect the graphics and smoothness quality, and (3) the control quality only depends on the client type (mobile versus desktop). To the best of our knowledge, such user studies have never been done in the literature.

量化「樂趣」－以心理生理量測探究數位娛樂商品之市場價值Academia Sinica

On The Battle between Online Gamers and Lags

Academia Sinica

Although online games have been an important Internet activity today, players inevitably suffer from lag from time to time due to the Internet’s non-QoS-guaranteed architecture. Here by lag we refer to the phenomena when a game fails to respond to user commands or update the screen in a timely fashion due to long system processing or network delays. Currently, little is known about how game players feel about lag and how they react when encountering lag during game play. In this paper, we present an Internet survey that is designed to understand the following questions: 1) How do players perceive lag, 2) what do players think of the causes of lag, and 3) how do players react to lag. Our results show that game players often struggle with lag, because they are unable to identify the root cause. Therefore, they have to try any combination of possible solutions found on the Internet, blame game companies, or learn to cope. These findings manifest a strong demand for an automatic diagnostic tool that can identify the root cause of lag for gamers.

Understanding The Performance of Thin-Client Gaming

Academia Sinica

The thin-client model is considered a perfect fit for online gaming. As modern games normally require tremendous computing and rendering power at the game client, deploying games with such models can transfer the burden of hardware upgrades from players to game operators. As a result, there are a variety of solutions proposed for thin-client gaming today. However, little is known about the performance of such thinclient systems in different scenarios, and there is no systematic means yet to conduct such analysis. In this paper, we propose a methodology for quantifying the performance of thin-clients on gaming, even for thin-clients which are close-sourced. Taking a classic game, Ms. Pac-Man, and three popular thin-clients, LogMeIn, TeamViewer, and UltraVNC, as examples, we perform a demonstration study and determine that 1) display frame rate and frame distortion are both critical to gaming; and 2) different thin-client implementations may have very different levels of robustness against network impairments. Generally, LogMeIn performs best when network conditions are reasonably good, while TeamViewer and UltraVNC are the better choices under certain network conditions.

Quantifying QoS Requirements of Network Services: A Cheat-Proof Framework

Academia Sinica

Despite all the efforts devoted to improving the QoS of networked multimedia services, the baseline for such improvements has yet to be defined. In other words, although it is well recognized that better network conditions generally yield better service quality, the exact minimum level of network QoS required to ensure satisfactory user experience remains an open question. In this paper, we propose a general, cheat-proof framework that enables researchers to systematically quantify the minimum QoS needs for real-time networked multimedia services. Our framework has two major features: 1) it measures the quality of a service that users find intolerable by intuitive responses and therefore reduces the burden on experiment participants; and 2) it is cheat-proof because it supports systematic verification of the participants' inputs. Via a pilot study involving 38 participants, we verify the efficacy of our framework by proving that even inexperienced participants can easily produce consistent judgments. In addition, by cross-application and cross-service comparative analysis, we demonstrate the usefulness of the derived QoS thresholds. Such knowledge will serve important reference in the evaluation of competitive applications, application recommendation, network planning, and resource arbitration.

Online Game QoE Evaluation using Paired Comparisons

Academia Sinica

To satisfy players' gaming experience, there is a strong need for a technique that can measure a game's quality systemically, efficiently, and reliably. In this paper, we propose to use paired comparisons and probabilistic choice models to quantify online games's QoE under various network situations. The advantages of our methodology over the traditional MOS ratings are 1) the rating procedure is simpler thus less burden is on experiment participants, 2) it derives ratio-scale scores, and 3) it enables systematic verification of participants' inputs. As a demonstration, we apply our methodology to evaluate three popular FPS (first-person-shooter) games, namely, Alien Arena (Alien), Halo, and Unreal Tournament (UT), and investigate their network robustness. The results indicate that Halo performs the best in terms of their network robustness against packet delay and loss. However, if we take the degree of the games' sophistication into account, we consider that the robustness of UT against downlink delays should able be improved. We also show that our methodology can be a helpful tool for making decisions about design alternatives, such how dead reckoning algorithms and time synchronization mechanisms should be implemented.

GamingAnywhere: An Open Cloud Gaming System

Academia Sinica

Cloud gaming is a promising application of the rapidly expanding cloud computing infrastructure. Existing cloud gaming systems, however, are closed-source with proprietary protocols, which raises the bars to setting up testbeds for experiencing cloud games. In this paper, we present a complete cloud gaming system, called GamingAnywhere, which is to the best of our knowledge the first open cloud gaming system. In addition to its openness, we design GamingAnywhere for high extensibility, portability, and reconfigurability. We implement GamingAnywhere on Windows, Linux, and OS X, while its client can be readily ported to other OS's, including iOS and Android. We conduct extensive experiments to evaluate the performance of GamingAnywhere, and compare it against two well-known cloud gaming systems: OnLive and StreamMyGame. Our experimental results indicate that GamingAnywhere is efficient and provides high responsiveness and video quality. For example, GamingAnywhere yields a per-frame processing delay of 34 ms, which is 3+ and 10+ times shorter than OnLive and StreamMyGame, respectively. Our experiments also reveal that all these performance gains are achieved without the expense of higher network loads; in fact, GamingAnywhere incurs less network traffic. The proposed GamingAnywhere can be employed by the researchers, game developers, service providers, and end users for setting up cloud gaming testbeds, which, we believe, will stimulate more research innovations on cloud gaming systems. GamingAnywhere is now publicly available at http://gaminganywhere.org.

Are All Games Equally Cloud-Gaming-Friendly? An Electromyographic Approach

Academia Sinica

Cloud gaming makes any computer game playable on a thin client without worrying the hardware requirements as before. It frees players from the need to constantly upgrade their computers as they can now play games that host on remote servers with a broadband Internet connection and a thin client. However, cloud games are intrinsically more susceptible to latency than online games because game graphics are rendered on server nodes and thin clients do not possess game state information that is required by delay compensation techniques. In this paper, we investigate how the response latency would affect users' experience when playing games on clouds and how the impact of latency on players' experience varies across different games. We show that not all games are equally friendly to cloud gaming. The same degree of latency may have very different impact on a game's quality of experience depending on the game's real-time strictness. We thus develop a model that can predict a game's real-time strictness based on the rate of players' inputs and game screen dynamics. The model can be used to enhance players' experience in cloud gaming and optimize data center operation cost simultaneously.

Forecasting Online Game Addictiveness

Academia Sinica

1) The document discusses predicting the addictiveness and lifetime of online games using player behavior data and facial electromyography measurements of emotions. 2) An addictiveness index is defined based on the decline rate of the ratio of player presence over time, and facial muscle activity is measured to quantify emotional responses to different games. 3) A model is created relating emotional strength measurements to addictiveness indexes with 94% accuracy, and is validated with 11% average error rate at predicting addictiveness of unseen games. This could help optimize game development and investment decisions.

Identifying MMORPG Bots: A Traffic Analysis Approach

Academia Sinica

The document proposes four strategies to detect bots in MMORPG games by analyzing network traffic patterns without intruding on players' experiences. It describes collecting network traces from both human players and bots in Ragnarok Online. The strategies analyze timing of commands, burstiness of traffic over time, and compare client and server traffic burstiness to identify patterns characteristic of bot behavior, such as highly regular response times and smoother traffic patterns than humans. A decision framework determines if a traffic stream indicates bot control based on these strategies.

Toward an Understanding of the Processing Delay of Peer-to-Peer Relay Nodes

Academia Sinica

Peer-to-peer relaying is commonly used in realtime applications to cope with NAT and firewall restrictions and provide better quality network paths. As relaying is not natively supported by the Internet, it is usually implemented at the application layer. Also, in a modern operating system, the processor is shared, so the receive-process-forward process for each relay packet may take a considerable amount of time if the host is busy handling some other tasks. Thus, if we happen to select a loaded relay node, the relaying may introduce significant delays to the packet transmission time and even degrade the application performance. In this work, based on an extensive set of Internet traces, we pursue an understanding of the processing delays incurred at relay nodes and their impact on the application performance. Our contribution is three-fold: 1) we propose a methodology for measuring the processing delays at any relay node on the Internet; 2) we characterize the workload patterns of a variety of Internet relay nodes; and 3) we show that, serious VoIP quality degradation may occur due to relay processing, thus we have to monitor the processing delays of a relay node continuously to prevent the application performance from being degraded.

Game Bot Detection Based on Avatar Trajectory

Academia Sinica

In recent years, online gaming has become one of the most popular Internet activities, but cheating activity, such as the use of game bots, has increased as a consequence. Generally, the gaming community disagrees with the use of game bots, as bot users obtain unreasonable rewards without corresponding efforts. However, bots are hard to detect because they are designed to simulate human game playing behavior and they follow game rules exactly. Existing detection approaches either interrupt the players’gaming experience, or they assume game bots are run as standalone clients or assigned a specific goal, such as aim bots in FPS games. In this paper, we propose a trajectory-based approach to detect game bots. It is a general technique that can be applied to any game in which the avatar’s movement is controlled directly by the players. Through real-life data traces, we show that the trajectories of human players and those of game bots are very different. In addition, although game bots may endeavor to simulate players’ decisions, certain human behavior patterns are difficult to mimic because they are AI-hard. Taking Quake 2 as a case study, we evaluate our scheme’s performance based on reallife traces. The results show that the scheme can achieve a detection accuracy of 95% or higher given a trace of 200 seconds or longer.

Improving Reliability of Web 2.0-based Rating Systems Using Per-user TrustinessAcademia Sinica

A Collusion-Resistant Automation Scheme for Social Moderation Systems

Academia Sinica

This document summarizes a research paper on developing a collusion-resistant automation scheme for social moderation systems. The researchers propose a community-based scheme that analyzes accusation relations between users to distinguish genuine accusations from malicious ones made by colluders. It clusters users based on incoming and outgoing accusation features to label misbehaving users. Simulation results show the scheme achieves over 90% accuracy in identifying misbehaving users and prevents 90% of victims from false accusations due to collusion. The community-based approach improves over simple count-based schemes that are vulnerable to collusion attacks.

Tuning Skype’s Redundancy Control Algorithm for User Satisfaction

Academia Sinica

Determining how to transport delay-sensitive voice data has long been a problem in multimedia networking. The difficulty arises because voice and best-effort data are different by nature. It would not be fair to give priority to voice traffic and starve its best-effort counterpart; however, the voice data delivered might not be perceptible if each voice call is limited to the rate of an average TCP flow. To address the problem, we approach it from a user-centric perspective by tuning the voice data rate based on user satisfaction. Our contribution in this work is threefold. First, we investigate how Skype, the largest and fastest growing VoIP service on the Internet, adapts its voice data rate (i.e., the redundancy ratio) to network conditions. Second, by exploiting implementations of public domain codecs, we discover that Skype’s mechanism is not really geared to user satisfaction. Third, based on a set of systematic experiments that quantify user satisfaction under different levels of packet loss and burstiness, we derive a concise model that allows user-centric redundancy control. The model can be easily incorporated into general VoIP services (not only Skype) to ensure consistent user satisfaction.

Network Game Design: Hints and Implications of Player Interaction

Academia Sinica

While psychologists analyze network game-playing behavior in terms of players’ social interaction and experience, understanding user behavior is equally important to network researchers, because how users act determines how well network systems, such as online games, perform. To gain a better understanding of patterns of player interaction and their implications for game design, we analyze a 1, 356-millionpacket trace of ShenZhou Online, a mid-sized commercial MMORPG. This work is dedicated to draw out hints and implications of player interaction patterns, which is inferred from network-level traces, for online games. We find that the dispersion of players in a virtual world is heavy-tailed, which implies that static and fixed-size partitioning of game worlds is inadequate. Neighbors and teammates tend to be closer to each other in network topology. This property is an advantage, because message delivery between the hosts of interacting players can be faster than between those of unrelated players. In addition, the property can make game playing fairer, since interacting players tend to have similar latencies to their servers. We also find that participants who have a higher degree of social interaction tend to play much longer, and players who are closer in network topology tend to team up for longer periods. This suggests that game designers could increase the “stickiness” of games by encouraging, or even forcing, team playing.

More from Academia Sinica (20)

Computational Social Science:The Collaborative Futures of Big Data, Computer ...

Games on Demand: Are We There Yet?

Detecting In-Situ Identity Fraud on Social Network Services: A Case Study on ...

Cloud Gaming Onward: Research Opportunities and Outlook

Quantifying User Satisfaction in Mobile Cloud Games

量化「樂趣」－以心理生理量測探究數位娛樂商品之市場價值

On The Battle between Online Gamers and Lags

Understanding The Performance of Thin-Client Gaming

Quantifying QoS Requirements of Network Services: A Cheat-Proof Framework

Online Game QoE Evaluation using Paired Comparisons

GamingAnywhere: An Open Cloud Gaming System

Are All Games Equally Cloud-Gaming-Friendly? An Electromyographic Approach

Forecasting Online Game Addictiveness

Identifying MMORPG Bots: A Traffic Analysis Approach

Toward an Understanding of the Processing Delay of Peer-to-Peer Relay Nodes

Game Bot Detection Based on Avatar Trajectory

Improving Reliability of Web 2.0-based Rating Systems Using Per-user Trustiness

A Collusion-Resistant Automation Scheme for Social Moderation Systems

Tuning Skype’s Redundancy Control Algorithm for User Satisfaction

Network Game Design: Hints and Implications of Player Interaction

Recently uploaded

"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk

Fwdays

At this talk we will discuss DDoS protection tools and best practices, discuss network architectures and what AWS has to offer. Also, we will look into one of the largest DDoS attacks on Ukrainian infrastructure that happened in February 2022. We'll see, what techniques helped to keep the web resources available for Ukrainians and how AWS improved DDoS protection for all customers based on Ukraine experience

Driving Business Innovation: Latest Generative AI Advancements & Success Story

Safe Software

Are you ready to revolutionize how you handle data? Join us for a webinar where we’ll bring you up to speed with the latest advancements in Generative AI technology and discover how leveraging FME with tools from giants like Google Gemini, Amazon, and Microsoft OpenAI can supercharge your workflow efficiency. During the hour, we’ll take you through: Guest Speaker Segment with Hannah Barrington: Dive into the world of dynamic real estate marketing with Hannah, the Marketing Manager at Workspace Group. Hear firsthand how their team generates engaging descriptions for thousands of office units by integrating diverse data sources—from PDF floorplans to web pages—using FME transformers, like OpenAIVisionConnector and AnthropicVisionConnector. This use case will show you how GenAI can streamline content creation for marketing across the board. Ollama Use Case: Learn how Scenario Specialist Dmitri Bagh has utilized Ollama within FME to input data, create custom models, and enhance security protocols. This segment will include demos to illustrate the full capabilities of FME in AI-driven processes. Custom AI Models: Discover how to leverage FME to build personalized AI models using your data. Whether it’s populating a model with local data for added security or integrating public AI tools, find out how FME facilitates a versatile and secure approach to AI. We’ll wrap up with a live Q&A session where you can engage with our experts on your specific use cases, and learn more about optimizing your data workflows with AI. This webinar is ideal for professionals seeking to harness the power of AI within their data management systems while ensuring high levels of customization and security. Whether you're a novice or an expert, gain actionable insights and strategies to elevate your data processes. Join us to see how FME and AI can revolutionize how you work with data!

Fueling AI with Great Data with Airbyte Webinar

Zilliz

Y-Combinator seed pitch deck template PP

c5vrf27qcz

Principle of conventional tomography-Bibash Shahi ppt..pptx

BibashShahi

Astute Business Solutions | Oracle Cloud Partner |

AstuteBusiness

Choosing The Best AWS Service For Your Website + API.pptx

Brandon Minnick, MBA

Have you ever been confused by the myriad of choices offered by AWS for hosting a website or an API? Lambda, Elastic Beanstalk, Lightsail, Amplify, S3 (and more!) can each host websites + APIs. But which one should we choose? Which one is cheapest? Which one is fastest? Which one will scale to meet our needs? Join me in this session as we dive into each AWS hosting service to determine which one is best for your scenario and explain why!

5th LF Energy Power Grid Model Meet-up Slides

DanBrown980551

5th Power Grid Model Meet-up It is with great pleasure that we extend to you an invitation to the 5th Power Grid Model Meet-up, scheduled for 6th June 2024. This event will adopt a hybrid format, allowing participants to join us either through an online Mircosoft Teams session or in person at TU/e located at Den Dolech 2, Eindhoven, Netherlands. The meet-up will be hosted by Eindhoven University of Technology (TU/e), a research university specializing in engineering science & technology. Power Grid Model The global energy transition is placing new and unprecedented demands on Distribution System Operators (DSOs). Alongside upgrades to grid capacity, processes such as digitization, capacity optimization, and congestion management are becoming vital for delivering reliable services. Power Grid Model is an open source project from Linux Foundation Energy and provides a calculation engine that is increasingly essential for DSOs. It offers a standards-based foundation enabling real-time power systems analysis, simulations of electrical power grids, and sophisticated what-if analysis. In addition, it enables in-depth studies and analysis of the electrical power grid’s behavior and performance. This comprehensive model incorporates essential factors such as power generation capacity, electrical losses, voltage levels, power flows, and system stability. Power Grid Model is currently being applied in a wide variety of use cases, including grid planning, expansion, reliability, and congestion studies. It can also help in analyzing the impact of renewable energy integration, assessing the effects of disturbances or faults, and developing strategies for grid control and optimization. What to expect For the upcoming meetup we are organizing, we have an exciting lineup of activities planned: -Insightful presentations covering two practical applications of the Power Grid Model. -An update on the latest advancements in Power Grid -Model technology during the first and second quarters of 2024. -An interactive brainstorming session to discuss and propose new feature requests. -An opportunity to connect with fellow Power Grid Model enthusiasts and users.

Introduction of Cybersecurity with OSS at Code Europe 2024

Hiroshi SHIBATA

I develop the Ruby programming language, RubyGems, and Bundler, which are package managers for Ruby. Today, I will introduce how to enhance the security of your application using open-source software (OSS) examples from Ruby and RubyGems. The first topic is CVE (Common Vulnerabilities and Exposures). I have published CVEs many times. But what exactly is a CVE? I'll provide a basic understanding of CVEs and explain how to detect and handle vulnerabilities in OSS. Next, let's discuss package managers. Package managers play a critical role in the OSS ecosystem. I'll explain how to manage library dependencies in your application. I'll share insights into how the Ruby and RubyGems core team works to keep our ecosystem safe. By the end of this talk, you'll have a better understanding of how to safeguard your code.

GNSS spoofing via SDR (Criptored Talks 2024)

Javier Junquera

In the realm of cybersecurity, offensive security practices act as a critical shield. By simulating real-world attacks in a controlled environment, these techniques expose vulnerabilities before malicious actors can exploit them. This proactive approach allows manufacturers to identify and fix weaknesses, significantly enhancing system security. This presentation delves into the development of a system designed to mimic Galileo's Open Service signal using software-defined radio (SDR) technology. We'll begin with a foundational overview of both Global Navigation Satellite Systems (GNSS) and the intricacies of digital signal processing. The presentation culminates in a live demonstration. We'll showcase the manipulation of Galileo's Open Service pilot signal, simulating an attack on various software and hardware systems. This practical demonstration serves to highlight the potential consequences of unaddressed vulnerabilities, emphasizing the importance of offensive security practices in safeguarding critical infrastructure.

Taking AI to the Next Level in Manufacturing.pdf

ssuserfac0301

Read Taking AI to the Next Level in Manufacturing to gain insights on AI adoption in the manufacturing industry, such as: 1. How quickly AI is being implemented in manufacturing. 2. Which barriers stand in the way of AI adoption. 3. How data quality and governance form the backbone of AI. 4. Organizational processes and structures that may inhibit effective AI adoption. 6. Ideas and approaches to help build your organization's AI strategy.

Generating privacy-protected synthetic data using Secludy and Milvus

Zilliz

During this demo, the founders of Secludy will demonstrate how their system utilizes Milvus to store and manipulate embeddings for generating privacy-protected synthetic data. Their approach not only maintains the confidentiality of the original data but also enhances the utility and scalability of LLMs under privacy constraints. Attendees, including machine learning engineers, data scientists, and data managers, will witness first-hand how Secludy's integration with Milvus empowers organizations to harness the power of LLMs securely and efficiently.

“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...

Edge AI and Vision Alliance

For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/06/how-axelera-ai-uses-digital-compute-in-memory-to-deliver-fast-and-energy-efficient-computer-vision-a-presentation-from-axelera-ai/ Bram Verhoef, Head of Machine Learning at Axelera AI, presents the “How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-efficient Computer Vision” tutorial at the May 2024 Embedded Vision Summit. As artificial intelligence inference transitions from cloud environments to edge locations, computer vision applications achieve heightened responsiveness, reliability and privacy. This migration, however, introduces the challenge of operating within the stringent confines of resource constraints typical at the edge, including small form factors, low energy budgets and diminished memory and computational capacities. Axelera AI addresses these challenges through an innovative approach of performing digital computations within memory itself. This technique facilitates the realization of high-performance, energy-efficient and cost-effective computer vision capabilities at the thin and thick edge, extending the frontier of what is achievable with current technologies. In this presentation, Verhoef unveils his company’s pioneering chip technology and demonstrates its capacity to deliver exceptional frames-per-second performance across a range of standard computer vision networks typical of applications in security, surveillance and the industrial sector. This shows that advanced computer vision can be accessible and efficient, even at the very edge of our technological ecosystem.

Skybuffer SAM4U tool for SAP license adoption

Tatiana Kojar

Manage and optimize your license adoption and consumption with SAM4U, an SAP free customer software asset management tool. SAM4U, an SAP complimentary software asset management tool for customers, delivers a detailed and well-structured overview of license inventory and usage with a user-friendly interface. We offer a hosted, cost-effective, and performance-optimized SAM4U setup in the Skybuffer Cloud environment. You retain ownership of the system and data, while we manage the ABAP 7.58 infrastructure, ensuring fixed Total Cost of Ownership (TCO) and exceptional services through the SAP Fiori interface.

Your One-Stop Shop for Python Success: Top 10 US Python Development Providers

akankshawande

Dandelion Hashtable: beyond billion requests per second on a commodity server

Antonios Katsarakis

This slide deck presents DLHT, a concurrent in-memory hashtable. Despite efforts to optimize hashtables, that go as far as sacrificing core functionality, state-of-the-art designs still incur multiple memory accesses per request and block request processing in three cases. First, most hashtables block while waiting for data to be retrieved from memory. Second, open-addressing designs, which represent the current state-of-the-art, either cannot free index slots on deletes or must block all requests to do so. Third, index resizes block every request until all objects are copied to the new index. Defying folklore wisdom, DLHT forgoes open-addressing and adopts a fully-featured and memory-aware closed-addressing design based on bounded cache-line-chaining. This design offers lock-free index operations and deletes that free slots instantly, (2) completes most requests with a single memory access, (3) utilizes software prefetching to hide memory latencies, and (4) employs a novel non-blocking and parallel resizing. In a commodity server and a memory-resident workload, DLHT surpasses 1.6B requests per second and provides 3.5x (12x) the throughput of the state-of-the-art closed-addressing (open-addressing) resizable hashtable on Gets (Deletes).

Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...

saastr

Apps Break Data

Ivo Velitchkov

How information systems are built or acquired puts information, which is what they should be about, in a secondary place. Our language adapted accordingly, and we no longer talk about information systems but applications. Applications evolved in a way to break data into diverse fragments, tightly coupled with applications and expensive to integrate. The result is technical debt, which is re-paid by taking even bigger "loans", resulting in an ever-increasing technical debt. Software engineering and procurement practices work in sync with market forces to maintain this trend. This talk demonstrates how natural this situation is. The question is: can something be done to reverse the trend?

What is an RPA CoE? Session 1 – CoE Vision

DianaGray10

Digital Banking in the Cloud: How Citizens Bank Unlocked Their Mainframe

Precisely

Inconsistent user experience and siloed data, high costs, and changing customer expectations – Citizens Bank was experiencing these challenges while it was attempting to deliver a superior digital banking experience for its clients. Its core banking applications run on the mainframe and Citizens was using legacy utilities to get the critical mainframe data to feed customer-facing channels, like call centers, web, and mobile. Ultimately, this led to higher operating costs (MIPS), delayed response times, and longer time to market. Ever-changing customer expectations demand more modern digital experiences, and the bank needed to find a solution that could provide real-time data to its customer channels with low latency and operating costs. Join this session to learn how Citizens is leveraging Precisely to replicate mainframe data to its customer channels and deliver on their “modern digital bank” experiences.

Recently uploaded (20)

"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk

Driving Business Innovation: Latest Generative AI Advancements & Success Story

Fueling AI with Great Data with Airbyte Webinar

Y-Combinator seed pitch deck template PP

Principle of conventional tomography-Bibash Shahi ppt..pptx

Astute Business Solutions | Oracle Cloud Partner |

Choosing The Best AWS Service For Your Website + API.pptx

5th LF Energy Power Grid Model Meet-up Slides

Introduction of Cybersecurity with OSS at Code Europe 2024

GNSS spoofing via SDR (Criptored Talks 2024)

Taking AI to the Next Level in Manufacturing.pdf

Generating privacy-protected synthetic data using Secludy and Milvus

“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...

Skybuffer SAM4U tool for SAP license adoption

Your One-Stop Shop for Python Success: Top 10 US Python Development Providers

Dandelion Hashtable: beyond billion requests per second on a commodity server

Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...

Apps Break Data

What is an RPA CoE? Session 1 – CoE Vision

Digital Banking in the Cloud: How Citizens Bank Unlocked Their Mainframe

Inferring Speech Activity from Encrypted Skype Traffic

1. Inferring Speech Activity from Encrypted Skype Traffic Yu‐Chun Chang, Kuan‐Ta Chen, Chen‐Chi Wu, and Chin‐Laung Lei Oct. 27, 2008 2008/10/27 1

2. Outline • Introduction • Data description • Proposed scheme • Performance evaluation • Conclusion 2008/10/27 2

3. Introduction • VAD (Voice Activity Detection) – The algorithm to extract the presence or absence of human speech in speech processing. • Source‐level VAD – Audio signal – Silence suppression • Network‐level VAD – Network traffic – Flow identification, QoS measurement 2008/10/27 3

4. • The differences between source‐level and network‐ level VAD source‐level network‐level input audio signal network traffic location speaker’s host network node purpose silence suppression traffic management echo cancellation QoS measurement 2008/10/27 4

5. Introduction (contd.) • Challenges – Payload encryption – Skype do not support silence suppression • Contribution – We propose a network‐level VAD that can infers speech activity from encrypted and non‐silence‐ suppressed VoIP traffic. 2008/10/27 5

6. Data Description • Experiment setup (Chosen by Skype) 2008/10/27 Audio signal Network traffic 6

7. Data Description (contd.) • Trace summary Total # of traces # TCP # UDP 1839 1427 412 # Relay node Mean packet size Mean time period 1677 109.6 bytes 612.5 sec 2008/10/27 7

8. Proposed Scheme • The indicator of voice activity – packet size • Smoothing • Adaptive thresholding 2008/10/27 8

9. The indicator of voice activity – Packet size 2008/10/27 9

10. Smoothing • EWMA (Exponentially Weighted Moving Average) EWMA : Pi = λYi + (1 − λ ) Pi −1 (λ = 0.2) Y : Observed packet size P : Smoothed packet size 2008/10/27 10

11. Packet Size (bytes) Adaptive thresholding 2008/10/27 11

12. Adaptive thresholding (contd.) P : 140 bytes (P + T2)/2 = 110 bytes (P + T1)/2 = 107 bytes T2 : 80 bytes T1 : 74 bytes 2008/10/27 12

13. Adaptive thresholding (contd.) Packet Size (bytes) 2008/10/27 estimated ON periods 13

14. Performance Evaluation • Number of ON periods Number _ of _ estimated _ ON _ periods Number _ of _ true _ ON _ periods 2008/10/27 14

15. Performance Evaluation (contd.) • Average length of ON periods Mean _ length _ of _ estimated _ ON _ periods Mean _ length _ of _ true _ ON _ periods 2008/10/27 15

16. Performance Evaluation (contd.) • State correctness M _ and _ N ON period ‐> 1 M _ or _ N OFF period ‐> 0 True speech activity (M) : 0 0 1 1 1 0 0 0 1 1 0 1 1 0 0 0 0 0 1 1 1 1 1 0 Estimated speech activity (N): 0 1 1 1 1 0 0 0 1 0 0 1 1 0 0 0 0 1 1 1 0 1 1 1 M and N: 0 0 1 1 1 0 0 0 1 0 0 1 1 0 0 0 0 0 1 1 0 1 1 0 M or N: 0 1 1 1 1 0 0 0 1 1 0 1 1 0 0 0 0 1 1 1 1 1 1 1 2008/10/27 16

17. Performance Evaluation (contd.) • State correctness 2008/10/27 17

18. Conclusion • We propose the network‐level VAD which infers speech activity from network traffic instead of audio signal. • We propose a VAD algorithm that can extract voice activity from encrypted and non‐silence‐ suppressed VoIP network traffic. 2008/10/27 18

19. • Thanks 2008/10/27 19

20. Backup slides 2008/10/27 20

21. VAD on audio signaling volume = 10 * log(∑ Si2 ) i Static threshold : 183 db J.‐S. R. Jang, “Audio signal processing and recognition,” http://www.cs.nthu.edu.tw/jang 2008/10/27 21

22. 2008/10/27 22

23. I am a student of National Taiwan University. 2008/10/27 23

24. Performance Evaluation (contd.) • Number of ON periods 2008/10/27 24

25. Performance Evaluation (contd.) • Average length of ON periods 2008/10/27 25

26. Performance Evaluation (contd.) • State correctness M ∩N M ∪N True speech activity (M) : 0 0 1 1 1 0 0 0 1 1 0 1 1 0 0 0 0 0 1 1 1 1 1 0 Estimated speech activity (N): 0 1 1 1 1 0 0 0 1 0 0 1 1 0 0 0 0 1 1 1 0 1 1 1 2008/10/27 26

Inferring Speech Activity from Encrypted Skype Traffic

Recommended

Recommended

More Related Content

Similar to Inferring Speech Activity from Encrypted Skype Traffic

Similar to Inferring Speech Activity from Encrypted Skype Traffic (20)

More from Academia Sinica

More from Academia Sinica (20)

Recently uploaded

Recently uploaded (20)

Inferring Speech Activity from Encrypted Skype Traffic