Harm-Bearing

Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition

arXiv:2606.01837v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable capabilities in content synthesis and autonomous reasoning. Previous safety guardrails are primarily designed for unimodal textual input interception, leaving them vulnerable to cross-modal jailbreak attacks. However, regardless unimodal textual attack or cross-modal jailbreak, typically inclusive part of explicit harmful or sensitive content at the input level,...