Whispering Agents: A Event-Driven Covert Communication Protocol for the Internet of Agents

Authors

  • Kaibo Huang Beijing University of Posts and Telecommunications
  • Yukun Wei Beijing University of Posts and Telecommunications
  • WanshengWu Beijing University of Posts and Telecommunications
  • Tianhua Zhang Beijing University of Posts and Telecommunications
  • Zhongliang Yang Beijing University of Posts and Telecommunications
  • Linna Zhou Beijing University of Posts and Telecommunications

DOI:

https://doi.org/10.1609/aaai.v40i37.40380

Abstract

The emergence of the Internet of Agents (IoA) introduces critical challenges for communication privacy in sensitive, high-stakes domains. While standard Agent-to-Agent (A2A) protocols secure message content, they are not designed to protect the act of communication itself, leaving agents vulnerable to surveillance and traffic analysis. We find that the rich, event-driven nature of agent dialogues provides a powerful, yet untapped, medium for covert communication. To harness this potential, we introduce and formalize the Covert Event Channel, the first unified model for agent covert communication driven by three interconnected dimensions, which consist of the Storage, Timing, and Behavioral channels. Based on this model, we design and engineer Pi-CCAP, a novel protocol that operationalizes this event-driven paradigm. Our comprehensive evaluation demonstrates that Pi-CCAP achieves high capacity and robustness while remaining imperceptible to powerful LLM-based wardens, establishing its practical viability. By systematically engineering this channel, our work provides the foundational understanding essential for developing the next generation of monitoring systems and defensive protocols for a secure and trustworthy IoA.

Published

2026-03-14

How to Cite

Huang, K., Wei, Y., , W., Zhang, T., Yang, Z., & Zhou, L. (2026). Whispering Agents: A Event-Driven Covert Communication Protocol for the Internet of Agents. Proceedings of the AAAI Conference on Artificial Intelligence, 40(37), 31185–31192. https://doi.org/10.1609/aaai.v40i37.40380

Issue

Section

AAAI Technical Track on Natural Language Processing II