Abstract
Encryption Protocols e.g., HTTPS is utilized to secure the traffic between servers and clients for YouTube and other video streaming services, and to further secure the communication, VPNs are used. However, these protocols are not sufficient to hide the identity of the videos from someone who can sniff the network traffic. The present work explores the methodologies and features to identify the videos in a VPN and non-VPN network traffic. To identify such videos, a side-channel attack using a Sequential Convolution Neural Network is proposed. The results demonstrate that a sequence of bytes per second from even one-minute sniffing of network traffic is sufficient to predict the video with high accuracy. The accuracy is increased to 90% accuracy in the non-VPN, 66% accuracy in the VPN, and 77% in the mixed VPN and non-VPN traffic, for models with two-minute sniffing.
Highlights
In the era of Industry 4.0 and more efficient Internet connectivity worldwide, video streams are increasing rapidly
In Scenario D, the traffic traces of videos in auto-mode quality are tested in Virtual Private Networks (VPNs) traffic
All the traces of videos in auto-mode quality in the VPN traffic are labelled under one class (VPN) instead of their labels, and the traces of videos in auto-mode quality in the non-VPN traffic are labelled as non-VPN in Scenario E
Summary
In the era of Industry 4.0 and more efficient Internet connectivity worldwide, video streams are increasing rapidly. YouTube—Google’s video streaming service—is among the most popular video streaming services, where, in the USA alone, more than 80% of digital video viewers use YouTube for watching online videos As the traditional methods fail to identify individual videos in the network traffic, there is a need to develop new methods that can detect the videos in encrypted network traffic under VPN and non-VPN settings. The present work proposes a side-channel attack to identify videos in a VPN and non-VPN network traffic between YouTube servers and the clients. The present work uses a sequence of consecutive bytes per second (BPS) obtained from the traffic from a YouTube server to a client’s computer and is used as a distinctive feature for identifying the video. A side-channel attack that uses a Sequential Convolutional Neural Network is proposed to identify videos in a VPN and non-VPN network traffic.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
