PRACTICAL AND LIGHTWEIGHT DEFENSE AGAINST WEBSITE FINGERPRINTING

PRACTICAL AND LIGHTWEIGHT DEFENSE AGAINST WEBSITE FINGERPRINTING

ABSTRACT

Website fingerprinting is a passive network traffic analysis technique which enables an adversary to identify the website a user visited despite encryption and the use of privacy services such as Tor. Several website fingerprinting defenses built on top of Tor have been put forth in an attempt to guarantee a user’s privacy by concealing trace features important to classification. However, a number of the best defenses incur a high bandwidth and/or latency overhead. To combat this, new defenses have sought to be both lightweight – i.e., introduce a small amount of bandwidth overhead – and zero-delay to real network traffic. This work introduces a novel zero-delay and lightweight website fingerprinting defense, titled BRO, which conceals the feature-rich front of a trace while still enabling the obfuscation of features deeper into the trace without spreading the padding budget thin. BRO schedules padding with a randomized beta distribution that can skew to both the extreme left and right, keeping the applied padding clustered to a finite portion of a trace. This work specifically targets deep learning based attacks, which continue to be among the most accurate website fingerprinting attacks. Results show that BRO is a formidable defense and decreases the accuracy of a state-of-the-art deep learning based attack while still providing protection against machine learning based attacks that is on par with other defenses.

Related Project Materials

Abstract

This study is on challenges besetting the effective teaching and learning of biology in secondary school. The t...

ABSTRACT

This study explored the implications of overpopulation on teacher’s job performance in Odeda Local Go...