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

POP and PUSH: Demystifying and Defending against (Mach) Port-oriented...

Min Zheng (Orion Security Lab, Alibaba Group), Xiaolong Bai (Orion Security Lab, Alibaba Group), Yajin Zhou (Zhejiang University), Chao Zhang (Institute for Network Science and Cyberspace, Tsinghua University), Fuping Qu (Orion Security Lab, Alibaba Group)

Read More

What Remains Uncaught?: Characterizing Sparsely Detected Malicious URLs on...

Sayak Saha Roy, Unique Karanjit, Shirin Nilizadeh (The University of Texas at Arlington)

Read More

Evading Voltage-Based Intrusion Detection on Automotive CAN

Rohit Bhatia (Purdue University), Vireshwar Kumar (Indian Institute of Technology Delhi), Khaled Serag (Purdue University), Z. Berkay Celik (Purdue University), Mathias Payer (EPFL), Dongyan Xu (Purdue University)

Read More

Preventing and Detecting State Inference Attacks on Android

Andrea Possemato (IDEMIA and EURECOM), Dario Nisi (EURECOM), Yanick Fratantonio (EURECOM and Cisco Talos)

Read More