arXiv:2606. 02134v1 Announce Type: cross Abstract: Deep neural networks achieve strong performance on many supervised learning tasks but remain vulnerable to adversarial perturbations.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 31653v1 Announce Type: cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set.
arXiv:2606. 18454v1 Announce Type: cross Abstract: We present Veriphi, a GPU-accelerated neural network verification system that combines fast adversarial attacks with formal bound certification using alpha,beta-CROWN methods.
arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.
arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.
arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.
arXiv:2607. 04145v1 Announce Type: new Abstract: Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models.