← Search

Pratiksha Agrawal

1 accepted papers

2026

Membership Privacy Risks of Sharpness Aware Minimization

ICLR 2026poster

Optimization algorithms that seek flatter minima, such as Sharpness-Aware Minimization (SAM), are credited with improved generalization and robustness to noise. We ask whether such gains impact membership privacy. Surprisingly, we find that SAM is more prone to Membership Inference Attacks (MIA) tha…

Cited by 0SourceScholar