Author

Sarah Radway

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#cybersecurity Preprint Sep 2026

Privacy Leakage Through AI-mediated Analysis of Smartphone Data

Priva-See is built, an LLM-based inference system for app-collected user data that reflects the best understanding of how real-life adtech companies would leverage machine learning to build user profiles, and suggests changes to how smartphone OSes should gather user consent for data access, to better inform users abou...

Sarah Radway, Zoe Robert, Matthew Soto et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape

It is shown that a misaligned model can perform inference engine fingerprinting to determine the specific engine (e.g., vLLM, SGLang) which executes the model, and several ways that inference engines could be changed to make fingerprinting attacks more difficult are discussed.

Sarah Radway, Andrew Cheng, V. Reddi et al. · 0 citations