RMIA
PulseAugur coverage of RMIA — every cluster mentioning RMIA across labs, papers, and developer communities, ranked by signal.
-
New method estimates AI model privacy risks without reference models
Researchers have developed a new method to estimate the vulnerability of AI models to membership inference attacks (MIAs) without needing to train separate reference models. This approach analyzes the loss distributions…
-
New framework unifies privacy attacks, introduces Bayesian approach
Researchers have unified three leading membership inference attacks (MIAs) – LiRA, RMIA, and BASE – under a single exponential-family log-likelihood ratio framework. This unification reveals a hierarchy of model complex…
-
New method traces AI model training data via semantic correlations
Researchers have developed a new method called idSCD to identify specific datasets used in training AI models. This technique analyzes the semantic correlation structure learned by a model, looking for incidental regula…