PerfWeb: How to Violate Web Privacy with Hardware Performance Events

Abstract

The browser history reveals highly sensitive information about users, such as financial status, health conditions, or political views. Private browsing modes and anonymity networks are consequently important tools to preserve the privacy not only of regular users but in particular of whistleblowers and dissidents. Yet, in this work we show how a malicious application can infer opened websites from Google Chrome in Incognito mode and from Tor Browser by exploiting hardware performance events (HPEs). In particular, we analyze the browsers' microarchitectural footprint with the help of advanced Machine Learning techniques: k-th Nearest Neighbors, Decision Trees, Support Vector Machines, and in contrast to previous literature also Convolutional Neural Networks. We profile 40 different websites, 30 of the top Alexa sites and 10 whistleblowing portals, on two machines featuring an Intel and an ARM processor. By monitoring retired instructions, cache accesses, and bus cycles for at most 5 seconds, we manage to classify the selected websites with a success rate of up to 86.3%. The results show that hardware performance events can clearly undermine the privacy of web users. We therefore propose mitigation strategies that impede our attacks and still allow legitimate use of HPEs.

Leaked-Web: Accurate and Efficient Machine Learning-Based Website Fingerprinting Attack through Hardware Performance Counters

“…This observation becomes more noticeable as we reduce the traces to lower than 20 where the accuracy becomes below to 80% for all the applied ML classification models. Another interesting observation is that Logit-RandomF classifier outperforms the previous work Perf-Web [9] for most of the training sizes (except when the number of traces for training drops to 5). When training traces is 50, Logit-RandomF classifier achieves the highest classification accuracy and F-measure, 91% and 0.901 respectively.…”

“…Once the side-channel information is collected, MLbased classification is leveraged to infer users' visited website information. There are three popular threat models targeting stealing users' browsing history, including native attack model [9], malicious website attack model [31], and hardware attack model [5].…”

“…It also enhances systems' security by providing microarchitectural information of malware, side-channel attacks, and building detectors based on the events' information [7], [16], [50]. However, recent studies have shown the suitability of such HPCs-based classification for spying on users' behaviors and violating users' privacy [9], [25]. Such privacy breach attacks gain access to HPCs via Perf tool which is a Linux-based low-level performance monitoring tool and provides considerable functionality and abstraction in the kernel, making the interface straightforward for ordinary users [1], [6].…”

“…Though effective, they only work for attacks deployed through malicious websites. Furthermore, advanced attacks [9] can be deployed in native code and bypass such detection systems. [27] randomizes properties, like offsetHeight and plugins, to the JavaScript environment, which generates different fingerprints even for the same website and increases non-determinism for attackers.…”

“…The Tor Browser based on the Firefox web browser further protects users by disabling features that may be used for tracking users.Despite considerable progress on developing users' privacy protections mechanisms, there are still a number of recent privacy violation attacks that rely on the application of Machine Learning (ML) algorithms that are trained with computer systems' side-channel information collected when a website is open. These attacks stem from existing sidechannel vulnerabilities like systems power analysis [20], CPU activity [4], on-chip cache memories [31], memory footprints [13], storage [17], and hardware events [9]. In this work, we comprehensively reviewed the existing studies on web browser fingerprinting attacks and identified some important challenges associated with these methods that could potentially result in underestimation of the security threats.…”