Our paper “SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)" was accepted at the IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) 2025 taking place in Copenhagen. We were lucky enough to, out of all papers, win the best paper award! It’s a great recognition for our recent summary on the fast-moving field of MIAs against LLMs.
