Shuo Shi

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.