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 the study of SCO largely unexplored. To this end, we propose StructBreak, an automated end-to-end framework designed to quantify SCO. By leveraging StructBreak, we uncover a novel higher-order cognitive overload attack paradigm; notably, this attack operates under a practical black-box setting, requiring no internal model access. Consequently, we utilize this framework to establish a comprehensive benchmark spanning ten diverse threat scenarios. Empirical evaluations on six leading MLLMs reveal that SCO readily triggers toxic generation, yielding a 92% average ASR (up to 97% on Gemini 2.5). To elucidate the mechanism of SCO, we further conduct model-level interpretations spanning attention dynamics, latent space topology, and geometric analysis. Our findings reveal that StructBreak acts as a novel structural channel to circumvent safety filters. Furthermore, the limited efficacy of inherent safety mechanisms underscores that current alignment paradigms are insufficient for the era of complex multimodal reasoning.
| Comments: | 23 pages; accepted to Findings of ACL 2026. This paper contains examples of harmful content |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.25534 [cs.AI] |
| (or arXiv:2605.25534v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.25534 arXiv-issued DOI via DataCite (pending registration) |
From: Yang Luo [view email]
[v1]
Mon, 25 May 2026 07:41:51 UTC (2,690 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。