StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs 事件

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs arXiv:2605.25534v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term this phenomenon Structural Cognitive Overload (SCO), a byproduct of the contention between deep reasoning and safety alignment. However, prior work has predominantly targeted typographic and pixel-level perturbations, leaving