Book
Open access
Aug 2026
The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails
Unsafe Semantic Distillation is proposed, which aligns adversarial perturbations with distributional representations of unsafe content rather than prompt-specific instances, and achieves 84% attack success rates, outperforming existing methods and exposing fundamental vulnerabilities in current multimodal safety architectures.
Shuo Shi, Ruiping Yin, Naen Xu et al.
· Proceedings of the 32nd ACM... · 1 citation