arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2512. 12997v2 Announce Type: replace-cross Abstract: CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks.
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:2510. 09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge.
arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.
The paper introduces CLEAR, a lightweight, task‑agnostic post‑hoc method that enhances evidential robustness in deep learning models without retraining. CLEAR uses held‑out calibration data to map the geometry of the model’s latent space, then generates perturbation views at inference to detect latent conflict. When high conflict is found, CLEAR selectively reduces evidential strength while preserving evidence for latent‑consistent inputs, achieving significant improvements in OOD and adversarial AUROC on ImageNet→CUB and running much faster than competing methods.
arXiv:2608. 09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken.