分而治之：一种混合策略击败多模态大语言模型

Computer Science > Computation and Language arXiv:2412.16555 (cs) [Submitted on 21 Dec 2024 (v1), last revised 16 Sep 2026 (this version, v4)] Title:Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models Authors:Yanxu Mao, Peipei Liu, Tiehan Cui, Zhaoteng Yan, Congying Liu, Datao You View a PDF of the paper titled Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models, by Yanxu Mao and 5 other authors View PDF HTML (experimental) Abstract:Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly severe. Jailbreaking attacks, as an important method for detecting vulnerabilities in LLMs, have been explored by researchers who attempt to induce these models to generate harmful content through various attack methods. Nevertheless, existing jailbreaking methods face numerous limitations, such as excessive query counts, limited coverage of jailbreak modalities, low attack success rates, and simplistic evaluation methods. To overcome these constraints, this paper proposes a multimodal jailbreaking method: JMLLM. This method integrates multiple strategies to perform comprehensive jailbreak attacks across text, visual, and auditory modalities. Additionally, we contribute a new and comprehensive dataset for multimodal jailbreaking research: TriJail, which includes jailbreak prompts for all three modalities. Experiments on the TriJail dataset and the benchmark dataset AdvBench, conducted on 13 popular LLMs, demonstrate advanced attack success rates and significant reduction in time overhead. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2412.16555 [cs.CL] (or arXiv:2412.16555v4 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2412.16555 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yanxu Mao [view email] [v1] Sat, 21 Dec 2024 09:43:51 UTC (1,681 KB) [v2] Thu, 22 May 2025 13:27:09 UTC (1,684 KB) [v3] Thu, 29 May 2025 14:05:50 UTC (1,677 KB) [v4] Wed, 16 Sep 2026 17:52:00 UTC (2,162 KB) Full-text links: Access Paper: View a PDF of the paper titled Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models, by Yanxu Mao and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2024-12 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)