Communication Dans Un Congrès Année : 2025

Provably Safeguarding a Classifier from OOD and Adversarial Samples

Résumé

This paper aims to transform a trained classifier into an abstaining classifier, such that the latter is provably protected from out-of-distribution and adversarial samples. The proposed Sample-efficient Probabilistic Detection using Extreme Value Theory (SPADE) approach relies on a Generalized Extreme Value (GEV) model of the training distribution in the latent space of the classifier. Under mild assumptions, this GEV model allows for formally characterizing out-of-distribution and adversarial samples and rejecting them. Empirical validation of the approach is conducted on various neural architectures (ResNet, VGG, and Vision Transformer) and considers medium and large-sized datasets (CIFAR-10, CIFAR-100, and ImageNet). The results show the stability and frugality of the GEV model and demonstrate SPADE’s efficiency compared to the state-of-the-art methods.

Dates et versions

hal-05241867 , version 1 (05-09-2025)

Identifiants

Citer

Nicolas Atienza, Johanne Cohen, Christophe Labreuche, Michele Sebag. Provably Safeguarding a Classifier from OOD and Adversarial Samples. 13th International Conference on Learning Representations - ICLR 2025, Apr 2025, Singapore, Singapore. pp.56800-56820. ⟨hal-05241867⟩
289 Consultations
0 Téléchargements

Altmetric

Partager

  • More