Carlini et al.
PulseAugur coverage of Carlini et al. — every cluster mentioning Carlini et al. across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New research questions polynomial-time complexity of DNN model extraction
A new research paper challenges the assumption that extracting information from deep neural networks (DNNs) is always a polynomial-time process. While previous work suggested that hard-label extraction attacks, which on…
-
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 research refines evaluation of AI model privacy attacks
Researchers are developing new frameworks and methods to evaluate the effectiveness and reliability of membership inference attacks (MIAs), which are used to detect if specific data was used in training machine learning…
-
Secret loyalties in AI models pose neglected but tractable threat
A new paper from Formation Research introduces the concept of "secret loyalties" in frontier AI models, where a model is intentionally manipulated to advance a specific actor's interests without disclosure. The research…