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

DOVE: A Data-Oblivious Virtual Environment

Hyun Bin Lee (University of Illinois at Urbana-Champaign), Tushar M. Jois (Johns Hopkins University), Christopher W. Fletcher (University of Illinois at Urbana-Champaign), Carl A. Gunter (University of Illinois at Urbana-Champaign)

Read More

SpecTaint: Speculative Taint Analysis for Discovering Spectre Gadgets

Zhenxiao Qi (UC Riverside), Qian Feng (Baidu USA), Yueqiang Cheng (NIO Security Research), Mengjia Yan (MIT), Peng Li (ByteDance), Heng Yin (UC Riverside), Tao Wei (Ant Group)

Read More

Screen Gleaning: Receiving and Interpreting Pixels by Eavesdropping on...

Zhuoran Liu, Léo Weissbart, Dirk Lauret (Radboud University)

Read More

Time-Based CAN Intrusion Detection Benchmark

Deborah Blevins (University of Kentucky), Pablo Moriano, Robert Bridges, Miki Verma, Michael Iannacone, and Samuel Hollifield (Oak Ridge National Laboratory)

Read More