Double-Layered Anti-Interception Strategy for Ground Combat Vehicles

Today, Warfighter Information Network-Tactical (WIN-T) systems are facing significant challenges in providing communication services with both security and quality of service (QoS). State-of-the-art security solutions for WIN-T mainly focus on a single anti-interception technique, sacrificing QoS to prevent energy-based eavesdroppers. We propose a double-layered anti-interception strategy for WIN-T, combining both passive and active defense mechanisms to address this issue. We formulate a non-convex optimization problem that jointly optimizes jamming allocation (JA), power allocation (PA), and spreading factor assignment (SA). We approximate this problem using first-order Taylor approximation and then solve it using an iterative method combined with the difference of convex (DC) functions. To further reduce the computational complexity in the high-mobility environment of ground combat vehicles, we reformulate the problem using a Multi-Agent Deep Reinforcement Learning (MADRL) framework. Simulation results demonstrate that our MADRL approach approximates the optimal solution in near real-time. It also outperforms the state-of-the-art baselines in terms of both Low Probability Interception (LPI) and throughput, promising an efficient and adaptive solution for modern WIN-T systems in real-time.