Abhinav Palia

Researcher, Microsoft

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming

#1110 · Alexandra Chouldechova, A. Feder Cooper, Solon Barocas, Abhinav Palia, Dan Vann, Hanna Wallach

We argue that conclusions drawn about relative system safety or attack method efficacy via AI red teaming are often not supported by evidence provided by attack success rate (ASR) comparisons.