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

Zoom on the Keystrokes: Exploiting Video Calls for Keystroke...

Mohd Sabra (University of Texas at San Antonio), Anindya Maiti (University of Oklahoma), Murtuza Jadliwala (University of Texas at San Antonio)

Read More

Cross-National Study on Phishing Resilience

Shakthidhar Reddy Gopavaram (Indiana University), Jayati Dev (Indiana University), Marthie Grobler (CSIRO’s Data61), DongInn Kim (Indiana University), Sanchari Das (University of Denver), L. Jean Camp (Indiana University)

Read More

FARE: Enabling Fine-grained Attack Categorization under Low-quality Labeled Data

Junjie Liang (The Pennsylvania State University), Wenbo Guo (The Pennsylvania State University), Tongbo Luo (Robinhood), Vasant Honavar (The Pennsylvania State University), Gang Wang (University of Illinois at Urbana-Champaign), Xinyu Xing (The Pennsylvania State University)

Read More

My Past Dictates my Present: Relevance, Exposure, and Influence...

Shujaat Mirza, Christina Pöpper (New York University)

Read More