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

MINOS: A Lightweight Real-Time Cryptojacking Detection System

Faraz Naseem (Florida International University), Ahmet Aris (Florida International University), Leonardo Babun (Florida International University), Ege Tekiner (Florida International University), A. Selcuk Uluagac (Florida International University)

Read More

SquirRL: Automating Attack Analysis on Blockchain Incentive Mechanisms with...

Charlie Hou (CMU, IC3), Mingxun Zhou (Peking University), Yan Ji (Cornell Tech, IC3), Phil Daian (Cornell Tech, IC3), Florian Tramèr (Stanford University), Giulia Fanti (CMU, IC3), Ari Juels (Cornell Tech, IC3)

Read More

From WHOIS to WHOWAS: A Large-Scale Measurement Study of...

Chaoyi Lu (Tsinghua University; Beijing National Research Center for Information Science and Technology), Baojun Liu (Tsinghua University; Beijing National Research Center for Information Science and Technology; Qi An Xin Group), Yiming Zhang (Tsinghua University; Beijing National Research Center for Information Science and Technology), Zhou Li (University of California, Irvine), Fenglu Zhang (Tsinghua University), Haixin Duan…

Read More

icLibFuzzer: Isolated-context libFuzzer for Improving Fuzzer Comparability

Yu-Chuan Liang, Hsu-Chun Hsiao (National Taiwan University)

Read More