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

Practical Blind Membership Inference Attack via Differential Comparisons

Bo Hui (The Johns Hopkins University), Yuchen Yang (The Johns Hopkins University), Haolin Yuan (The Johns Hopkins University), Philippe Burlina (The Johns Hopkins University Applied Physics Laboratory), Neil Zhenqiang Gong (Duke University), Yinzhi Cao (The Johns Hopkins University)

Read More

IoTSafe: Enforcing Safety and Security Policy with Real IoT...

Wenbo Ding (Clemson University), Hongxin Hu (University at Buffalo), Long Cheng (Clemson University)

Read More

Your Phone is My Proxy: Detecting and Understanding Mobile...

Xianghang Mi (University at Buffalo), Siyuan Tang (Indiana University Bloomington), Zhengyi Li (Indiana University Bloomington), Xiaojing Liao (Indiana University Bloomington), Feng Qian (University of Minnesota Twin Cities), XiaoFeng Wang (Indiana University Bloomington)

Read More

Demo #5: Securing Heavy Vehicle Diagnostics

Jeremy Daily, David Nnaji, and Ben Ettlinger (Colorado State University)

Read More