因互惠而不安全：生成-理解耦合如何削弱统一多模态模型的安全性

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.27332 (cs) [Submitted on 28 Mar 2026 (v1), last revised 15 Sep 2026 (this version, v2)] Title:Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models Authors:Kaishen Wang, Heng Huang View a PDF of the paper titled Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models, by Kaishen Wang and 1 other authors View PDF HTML (experimental) Abstract:Recent advances in Large Language Models (LLMs) and Text-to-Image (T2I) models have led to the emergence of Unified Multimodal Models (UMMs), where multimodal understanding and image generation are tightly integrated within a shared architecture. Prior studies suggest that such reciprocity enhances cross-functionality performance through shared representations and joint optimization. However, the safety implications of this tight coupling remain largely unexplored, as existing safety research predominantly analyzes understanding and generation functionalities in isolation. In this work, we investigate whether cross-functionality reciprocity itself constitutes a structural source of vulnerability in UMMs. We propose RICE: Reciprocal Interaction-based Cross-functionality Exploitation, a novel attack paradigm that explicitly exploits bidirectional interactions between understanding and generation. Using this framework, we systematically evaluate Generation-to-Understanding (G-U) and Understanding-to-Generation (U-G) attack pathways, demonstrating that unsafe intermediate signals can propagate across modalities and amplify safety risks. Extensive experiments show high Attack Success Rates (ASR) in both directions, revealing previously overlooked safety weaknesses inherent to UMMs. Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2603.27332 [cs.CV] (or arXiv:2603.27332v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2603.27332 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Kaishen Wang [view email] [v1] Sat, 28 Mar 2026 16:28:39 UTC (5,346 KB) [v2] Tue, 15 Sep 2026 13:37:22 UTC (5,344 KB) Full-text links: Access Paper: View a PDF of the paper titled Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models, by Kaishen Wang and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV new | recent | 2026-03 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?)