ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry

Computer Science > Artificial Intelligence [Submitted on 9 Apr 2026] ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry Wansheng Wu, Kaibo Huang, Yukun Wei, Zhongliang Yang, Linna Zhou As generative artificial intelligence evolves, autonomous agent networks present a powerful paradigm for interactive covert communication. However, because agents dynamically update internal memories via environmental interactions, existing methods face a critical structural vulnerability: cognitive asymmetry. Conventional approaches demand strict cognitive symmetry, requiring identical sequence prefixes between the encoder and decoder. In dynamic deployments, inevitable prefix discrepancies destroy synchronization, inducing severe channel degradation. To address this core challenge of cognitive asymmetry, we propose the Asymmetric Collaborative Framework (ACF), which structurally decouples covert communication from semantic reasoning via orthogonal statistical and cognitive layers. By deploying a prefix-independent decoding paradigm governed by a shared steganographic configuration, ACF eliminates the reliance on cognitive symmetry. Evaluations on realistic memory-augmented workflows demonstrate that under severe cognitive asymmetry, symmetric baselines suffer severe channel degradation, whereas ACF uniquely excels across both semantic fidelity and covert communication. It maintains computational indistinguishability, enabling reliable secret extraction with provable error bounds, and providing robust Effective Information Capacity guarantees for modern agent networks. Comments: 5 pages, 3 figures. Submitted to IEEE Signal Processing Letters (SPL). Source code is available at this https URL Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR) Cite as: arXiv:2604.08276 [cs.AI]   (or arXiv:2604.08276v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.08276 Focus to learn more Submission history From: Wansheng Wu [view email] [v1] Thu, 9 Apr 2026 14:10:51 UTC (178 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CR 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?)