Mohsen Imani

Graduation Semester and Year

2018

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Computer Science

Department

Computer Science and Engineering

First Advisor

Matthew Wright

Second Advisor

Gergely Zaruba

Third Advisor

Manfred Huber

Fourth Advisor

Farhad Kamangar

Abstract

Tor is an anonymity network that provides online privacy for the Internet users. Tor hides the user's traffic among the others' traffic. The more users Tor attracts, the stronger anonymity it provides. Unfortunately, users of the Tor anonymity system suffer from less-than-ideal performance, in part because circuit building and selection processes are not tuned for speed. Moreover, there are some attacks like guard fingerprinting and website fingerprinting attacks that try to profile or de-anonymize the Tor users. In this dissertation, we propose methods to address both security and performance issues in Tor. We first examine the process of selecting among pre-built circuits and the process of selecting the path of relays for use in building new circuits to improve performance while maintaining anonymity. We also propose a method to improve the mechanism of picking guards in Tor. The guard selection mechanism in Tor suffers from security problems like guard fingerprinting and from performance issues. To address this problem, we propose a new method for forming guard sets based on Internet location. We construct a hierarchy that keeps clients and guards together more reliably and prevents guards from easily joining arbitrary guard sets. This approach also has the advantage of confining an attacker with access to limited locations on the Internet to a small number of guard sets. Tor is also known to be vulnerable to the traffic analysis attacks like Website Fingerprinting (WF) attacks. In WF attacks, the adversary attempts to identify the websites visited by the user. We also propose a method using adversarial examples to decrease the accuracy rate of the WF attack. We generate adversarial traces to cause misclassification in the WF attackers. We show that if the WF attacker trains its classifier on the adversarial traces, they are not effective WF defenses. We propose a method to solve this problem, and we show that our method can drop the WF attacker's accuracy from 98% to 60% with 47% bandwidth overhead.

Keywords

Anonymity, Privacy, Tor network, Security

Disciplines

Computer Sciences | Physical Sciences and Mathematics

Comments

Degree granted by The University of Texas at Arlington

Download

Share

COinS