Agents

Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification

Single source1 source14 Oct 2026

arXiv:2610.15359v1 Announce Type: cross Abstract: Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.15359

← Back to all developments · Signals are a development reported by more than one source. See the methodology.