Inference on website fingerprinting

Lin, Weiran

Permalink

https://hdl.handle.net/2142/105422 Copy

Description

Title

Inference on website fingerprinting

Author(s)

Lin, Weiran

Contributor(s)

Borisov, Nikita

Issue Date

2018-12

Keyword(s)

• website fingerprinting
• server push
• HTTP/2

Date of Ingest

2019-09-10T20:05:16Z

Abstract

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.

Type of Resource

text

Genre of Resource

Dissertation / Thesis

Language

en

Permalink

http://hdl.handle.net/2142/105422

Owning Collections