AI RESEARCH
Sequential Membership Inference Attacks
arXiv CS.LG
•
ArXi:2602.16596v2 Announce Type: replace Modern AI models are not static. They go through multiple updates in their lifecycles. We propose to design Sequential Membership Inference (SeMI) attacks leading to tighter privacy audits by exploiting the sequence of models and injecting a target canary at a controlled insertion time. First, for empirical mean computation, we develop SeMI*, an {optimal SeMI attack to identify the presence of a target inserted at a specific insertion step