Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
Résumé
Conformal Prediction (CP) has proven to be an effective post-hoc method for improving the trustworthiness of neural networks by providing prediction sets with finite-sample guarantees. However, under adversarial attacks, classical conformal guarantees do not hold anymore: this problem is addressed in the field of Robust Conformal Prediction. Several methods have been proposed to provide robust CP sets with guarantees under adversarial perturbations, but for large-scale problems, these sets are either too large or the methods are too computationally demanding to be deployed in real-life scenarios. In this work, we propose a new method that leverages Lipschitz-bounded networks to precisely and efficiently estimate robust CP sets. When combined with a 1-Lipschitz robust network, we demonstrate that our lip-rcp method outperforms state-of-the-art results in both the size of the robust CP sets and computational efficiency in medium and large-scale scenarios such as ImageNet. Taking a different angle, we also study vanilla CP under attack and derive new worst-case coverage bounds of vanilla CP sets, which are valid simultaneously for all adversarial attack levels. Our lip-rcp method makes this second approach very efficient as well, as shown in the experiments.
Fichier principal
_ArXiv__Efficient_Robust_Conformal_Prediction_via_Lipschitz_Bounded_Networks.pdf (4)
Télécharger le fichier
[ArXiv] Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks.zip (4)
Télécharger le fichier
Origine | Fichiers produits par l'(les) auteur(s) |
---|