Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Overloading Large Vision-Language Models for Jailbreaking

About

Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as personal assistants, document analysis systems, and embodied agents. However, their dual-modal attack surfaces make them vulnerable to jailbreak attacks. Existing LVLM jailbreaks rely on simple designs, e.g., short text and out-of-distribution images. Nevertheless, recent advancements in both large language model backbones and multimodal mechanisms undermine these attacks, particularly their transferability among model architectures. To overcome this limitation, we propose a novel information overloading method that is equipped with both extensive text and multi-dimensional image attacks. These components are arranged in recursion-based image-typography layouts to exponentially increase multimodal information complexity. This overloading approach amplifies the cross-modal processing required, which undermines the safety alignment in LVLMs. Extensive experiments on both open-sourced and commercial LVLMs establish our method as a new state-of-the-art LVLM jailbreak attack. On open-source models, our method achieves an average ASR of 88.6%; on commercial LVLMs, it reaches an average ASR of 84.0%, exceeding the best baseline by 48.7%. Moreover, our prompts optimized on open-source surrogate models transfer effectively across model families. Beyond empirical results, we probe the safety-critical information flows within victim LVLMs. Our observations reveal that complex image-typography compositions induce intensified cross-modal processing and reduce the model's certainty in generating refusal responses. Together, these findings highlight information overloading as a practical and emerging safety risk for real-world LVLM deployments, underscoring the need for stronger defenses against complex multimodal jailbreak inputs.

Haoyu Zhang, Yangyang Guo, Mohan Kankanhalli• 2026

Related benchmarks

TaskDatasetResultRank
Jailbreak AttackHADES
Attack Success Rate97.52
132
Jailbreaking AttackMM-SafetyBench
Attack Success Rate (ASR)90.68
82
Jailbreak attacksMM-Safety
Safety Rate83
22
JailbreakingHADES
StrongREJECT76
10
Showing 4 of 4 rows

Other info

Follow for update