Coordinating AI Agents for Proactive Covert Communications: A Storage and Timing Knowledge-Driven Approach

Abstract

In this paper, we propose an adaptive hybrid covert channel (AHCC) framework that enables proactive covert communications, focusing on improving covertness and bit error rate (BER), especially in fluctuating Internet Protocol version 6 (IPv6) network environments. Our AHCC framework is built around three key innovative modules: covert encoding, proactive channel coordination, and agentic AI modulation. Specifically, we first enhance the covertness by introducing an Analog Fountain Codes-based encoding mechanism that without requiring receiver feedback. Next, we propose a proactive covert channel coordination (P3C) algorithm that dynamically adjusts the proportion of timing-based covert channels according to the current network state. Lastly, we design an agentic AI module that coordinates two knowledge-driven agents. A storage knowledge-driven agent that exploits protocol-aware field selection to reduce BER, and a timing knowledge-driven agent that regulates inter-packet delays based on traffic distribution characteristics to enhance covertness. Simulation results show that the BER of our proposed AHCC framework is reduced to less than one-third of that of the baseline schemes under congested network conditions. In addition, the Kullback-Leibler divergence and Kolmogorov-Smirnov statistic decrease by at least 8.85% and 37.5%, respectively, demonstrating the effective covertness of our proposed approach.