A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination

Computer Science > Cryptography and Security [Submitted on 3 Aug 2026] A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination Shiji Zhao, Yuxuan Zhou, Chen Xiong, Dongxian Wu, Yang Bai, Xun Chen Multimodal Large Language Models (MLLMs) have achieved impressive progress in image-text comprehension and generation, yet they remain susceptible to jailbreak attacks that can trigger harmful outputs and pose serious safety concerns. Existing multimodal jailbreak attacks have shown the feasibility of such attacks, but they still face two fundamental challenges: the lack of a atomic multi-modal strategy space, the absence of a concise and efficient executable framework beyond human-craft experience. To address these challenges, we first decompose the text-image jailbreak strategy space into three levels: structural, semantic, and syntactic, constructing a jailbreak strategy set encompassing both text and image modalities to systematically achieve combined coverage of different attack types. Then we propose a multimodal automated red team jailbreak method named Hierarchical Atomic Combination Attack (HACA). Specifically, based on a six-dimensional strategy space, a cross-modal joint planner is used to select and combine the different atomic jailbreak strategy for subsequent jailbreak command generation. Finally, at the implementation level, we explore to apply a unified generate executor to directly generate jailbreak instructions based on the selected multi-modal strategies. A series of experiments show that our automated red team method can achieve an attack success rate of average 95.48\% against five mainstream MLLMs. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2608.04034 [cs.CR]   (or arXiv:2608.04034v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.04034 Focus to learn more Submission history From: Shiji Zhao [view email] [v1] Mon, 3 Aug 2026 02:28:52 UTC (17,623 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)