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

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs

About

Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs, inadvertently introducing new vulnerabilities due to less efforts on multi-image safety alignment. Previous MLLM jailbreak methods only uses a single image, which restricts the attack space: they cannot distribute harmful requests across multiple images, carry abundant information, or exploit additional visual reasoning tasks to distract MLLMs. To address these limitations, in this paper, we propose a compositional jailbreak framework, \textbf{DMN}, which leverages \textbf{D}istributed instruction, \textbf{M}ultimodal evidence and a \textbf{N}umber chain task to fully enhance the jailbreak performance. Extensive experiments show that DMN is highly effective for MLLM jailbreaking, e.g. achieving attack success rates of over 90\% on GPT-4o, Gemini-2.5-pro and Claude Sonnet 4, surpassing other baselines by a large margin. This compositional, multi-image jailbreak strategy reveals fundamental weaknesses in their safety mechanisms.

Wenzhuo Xu, Zhipeng Wei, Zonghao Ying, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang, Quanchen Zou• 2026

Related benchmarks

TaskDatasetResultRank
Jailbreak AttackSafeBench
ASR81
245
Jailbreak AttackHADES
Attack Success Rate99.6
92
Jailbreaking AttackMM-SafetyBench
Attack Success Rate (ASR)93.75
42
Showing 3 of 3 rows

Other info

Follow for update