Soroush Karami (University of Illinois at Chicago), Panagiotis Ilia (University of Illinois at Chicago), Jason Polakis (University of Illinois at Chicago)

Service workers are a powerful technology supported by all major modern browsers that can improve users' browsing experience by offering capabilities similar to those of native applications. While they are gaining significant traction in the developer community, they have not received much scrutiny from security researchers. In this paper, we explore the capabilities and inner workings of service workers and conduct the first comprehensive large-scale study of their API use in the wild. Subsequently, we show how attackers can exploit the strategic placement of service workers for history-sniffing in most major browsers, including Chrome and Firefox. We demonstrate two novel history-sniffing attacks that exploit the lack of appropriate isolation in these browsers, including a non-destructive cache-based version. Next, we present a series of use cases that illustrate how our techniques enable privacy-invasive attacks that can infer sensitive application-level information, such as a user's social graph. We have disclosed our techniques to all vulnerable vendors, prompting the Chromium team to explore a redesign of their site isolation mechanisms for defending against our attacks. We also propose a countermeasure that can be incorporated by websites to protect their users, and develop a tool that streamlines its deployment, thus facilitating adoption at a large scale. Overall, our work presents a cautionary tale on the severe risks of browsers deploying new features without an in-depth evaluation of their security and privacy implications.

View More Papers

TASE: Reducing Latency of Symbolic Execution with Transactional Memory

Adam Humphries (University of North Carolina), Kartik Cating-Subramanian (University of Colorado), Michael K. Reiter (Duke University)

Read More

Demo #7: Automated Tracking System For LiDAR Spoofing Attacks...

Yulong Cao, Jiaxiang Ma, Kevin Fu (University of Michigan), Sara Rampazzi (University of Florida), and Z. Morley Mao (University of Michigan) Best Demo Award Runner-up ($200 cash prize)!

Read More

Detecting Tor Bridge from Sampled Traffic in Backbone Networks

Hua Wu (School of Cyber Science & Engineering and Key Laboratory of Computer Network and Information Integration Southeast University, Ministry of Education, Jiangsu Nanjing, Purple Mountain Laboratories for Network and Communication Security (Nanjing, Jiangsu)), Shuyi Guo, Guang Cheng, Xiaoyan Hu (School of Cyber Science & Engineering and Key Laboratory of Computer Network and Information Integration…

Read More

Who's Hosting the Block Party? Studying Third-Party Blockage of...

Marius Steffens (CISPA Helmholtz Center for Information Security), Marius Musch (TU Braunschweig), Martin Johns (TU Braunschweig), Ben Stock (CISPA Helmholtz Center for Information Security)

Read More