AI & ML
Dressed in Authority: Practical Black-Box Jailbreaking of MLLMs via Visual Trust Bias
arXiv cs.CR0 views
arXiv:2611.22292v1 Announce Type: new Abstract: 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.
Source:https://arxiv.org/abs/2611.22292PreviousFrom Token Changes to Task Failures: Bit Flips in a Shared KV-Cache BlockNextTetherMark: Instance-Level Watermark Authentication Against Cross-Instance Transplantation
Related posts

DeepSeek vs Claude vs Kimi vs Codex vs Gemini: A 70-Call AI Ethics Test
0dev.to
Fluent English is not evidence of ASL understanding: lessons from building a video translator
0dev.to

Audit Trails and Explainability for Agentic AI in Code Events
0dev.to
By 3 p.m. the daily high was already final on 78% of days. In Madrid, 32% (49 airports, one year)
0dev.to

This smell startup says its AI nose is as good as a human’s
0MIT Technology Review

Debugging Claude Fable 5.2 Code Art: Truncated SVG, Broken Canvas, Working Render
0dev.to