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

Demo #8: Security of Camera-based Perception for Autonomous Driving...

Christopher DiPalma, Ningfei Wang, Takami Sato, and Qi Alfred Chen (UC Irvine)

Read More

Mondrian: Comprehensive Inter-domain Network Zoning Architecture

Jonghoon Kwon (ETH Zürich), Claude Hähni (ETH Zürich), Patrick Bamert (Zürcher Kantonalbank), Adrian Perrig (ETH Zürich)

Read More

A First Look at Scams on YouTube

Elijah Bouma-Sims, Bradley Reaves (North Carolina State University)

Read More

Demo #3: Detecting Illicit Drone Video Filming Using Cryptanalysis

Ben Nassi, Raz Ben-Netanel (Ben-Gurion University of the Negev), Adi Shamir (Weizmann Institute of Science), and Yuval Elovic (Ben-Gurion University...

Read More