Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems

Computer Science > Cryptography and Security [Submitted on 27 May 2026] Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems Chenxi Wang, Ruiyang Huang, Jiayan Sun, Lei Wei, Yifan Wu Latent-based multi-agent systems replace parts of explicit inter-agent communication with hidden representations, offering a new direction for efficient and flexible agent collaboration. However, moving coordination into latent space may also move attacks beyond the reach of visible-text inspection. In this paper, we study whether latent states can carry attack-associated information that remains effective during clean executions. To examine this question, we introduce a latent attack framework that reactivates attack-induced effects through latent interventions without reusing adversarial text. Extensive experiments show that the resulting latent-only attacks can substantially degrade task performance in clean executions, especially when applied to inter-agent KV-cache handoffs rather than local hidden states. Further control analyses indicate that this degradation cannot be reduced to arbitrary perturbations or invalid generation. Overall, our findings suggest that latent-based collaboration does not remove attack risk. It shifts part of the risk into less observable execution states, calling for safeguards beyond visible-text inspection. Comments: 27 pages, 7 figures, 3 tables. Preprint Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG); Multiagent Systems (cs.MA) Cite as: arXiv:2605.28214 [cs.CR]   (or arXiv:2605.28214v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.28214 Focus to learn more Submission history From: Chenxi Wang [view email] [v1] Wed, 27 May 2026 09:32:22 UTC (1,855 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.LG cs.MA 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?)