Communication dans un congrès, AO, GALaC, Computer Science, Informatique

Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach

Nicolas Atienza, Christophe Labreuche, Johanne Cohen, Michèle Sebag. Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach. 13th International Conference on Learning Representations - ICLR 2025, Apr 2025, Singapore, Singapore. ⟨hal-04922382⟩

Published on