Although nowadays Internet users are better and better protected by advanced encryption mechanisms, their privacy is still not yet well protected: eavesdroppers can use the patterns of network traffic to learn sensitive information. One such attack is website fingerprinting, which adopts machine learning techniques to detect which webpage the user is visiting. In this thesis, we try to answer the question to what extent new web technologies, particularly HTTP/2 and server push, could interfere with website download packet traces, and hence defend against website fingerprinting. In our experiment, we extracted our website models from real-world sites and evaluated HTTP/2 server push and size padding with website fingerprinting on these models. The result shows that HTTP/2 and server push could lower the accuracy of website fingerprinting, and random size padding could further decrease this accuracy.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
