AI RESEARCH
Assessing Per-Sample Membership Inference Vulnerability without Retraining
arXiv CS.AI
•
ArXi:2602.15919v2 Announce Type: replace-cross Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the following question: can the privacy vulnerability of individual