Agents

Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving

Single source1 source7 Oct 2026

arXiv:2610.08331v1 Announce Type: cross Abstract: The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.08331

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