3 papers
cs.CR2026
Privacy Leakage Through AI-mediated Analysis of Smartphone Data
Sarah Radway, Zoe Robert, Matthew Soto +4
Over the past thirty years, the online advertising industry built a large-scale data collection ecosystem, with the goal of tracking a user's online activity to infer their demogra…
cs.CR2026
Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape
Sarah Radway, Andrew Cheng, Vijay Janapa Reddi +1
Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes per…
cs.CR2025
Guillotine: Hypervisors for Isolating Malicious AIs
James Mickens, Sarah Radway, Ravi Netravali
As AI models become more embedded in critical sectors like finance, healthcare, and the military, their inscrutable behavior poses ever-greater risks to society. To mitigate this r…