← 研踪 PaperTrailarXiv:2611.22292 · v1
Dressed in Authority: Practical Black-Box Jailbreaking of MLLMs via Visual Trust Bias
首次提交 2026-11-17 14:50
版本更新 2026-11-17 14:50
雷达观测 2026-11-18 19:43
摘要
Multimodal large language models (MLLMs) are rapidly advancing, yet their safety remains a critical concern, especially under jailbreak attempts. Existing MLLM jailbreaks either inject fragile adversarial perturbations into irrelevant images or synthesize toxic visual cues to achieve text-driven attack intents. In contrast, a more practical MLLM jailbreak emphasizes enhancing attack efficacy directly on naturally occurring harmful image-text pairs. We address this problem by proposing Visual Trust Bias Attack (VTBA), a new jailbreak framework that exploits a previously overlooked attack surface: MLLMs exhibit an intrinsic trust bias toward authoritative visual features, which enables transferable and stealthy jailbreaks. VTBA constructs a bank of authoritative templates, matches each input pair to the most relevant one, and integrates the harmful intent into the selected layout, thereby leveraging credible visual cues to override safety refusals while preserving naturalness. We further construct a dataset of 2,500 naturally occurring image-text pairs to evaluate jailbreaks in this practical multimodal setting. Extensive experiments show that our method consistently achieves high attack success rates across strong MLLMs, revealing a severe and previously underexplored weakness in current multimodal safety alignment. Warning: This paper may contain sensitive content.
作者备注:10 pages, 9 figures
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 14:50 · 最新观测版本
Dressed in Authority: Practical Black-Box Jailbreaking of MLLMs via Visual Trust Bias
Multimodal large language models (MLLMs) are rapidly advancing, yet their safety remains a critical concern, especially under jailbreak attempts. Existing MLLM jailbreaks either inject fragile adversarial perturbations into irrelevant images or synthesize toxic visual cues to achieve text-driven attack intents. In contrast, a more practical MLLM jailbreak emphasizes enhancing attack efficacy directly on naturally occurring harmful image-text pairs. We address this problem by proposing Visual Trust Bias Attack (VTBA), a new jailbreak framework that exploits a previously overlooked attack surface: MLLMs exhibit an intrinsic trust bias toward authoritative visual features, which enables transferable and stealthy jailbreaks. VTBA constructs a bank of authoritative templates, matches each input pair to the most relevant one, and integrates the harmful intent into the selected layout, thereby leveraging credible visual cues to override safety refusals while preserving naturalness. We further construct a dataset of 2,500 naturally occurring image-text pairs to evaluate jailbreaks in this practical multimodal setting. Extensive experiments show that our method consistently achieves high attack success rates across strong MLLMs, revealing a severe and previously underexplored weakness in current multimodal safety alignment. Warning: This paper may contain sensitive content.
查看此版本解读 →查看此版本原文 ↗