Secure Low-altitude Maritime Communications via Intelligent Jamming

TL;DR

The paper tackles secure maritime communications by leveraging a dual-UAV system where one UAV transmits data to a vessel and another intelligently jams a dynamic, uncertain eavesdropper. It formulates a secure and energy-efficient maritime communication multi-objective optimization problem (SEMCMOP) and reformulates it as a POMDP to handle time-varying channels and long-horizon trade-offs. To solve this NP-hard, dynamic problem, the authors propose SAC-CVAE, a GenAI-enhanced DRL algorithm that uses a CVAE-based policy disentanglement and an LSTM predictor to manage high-dimensional state spaces and multimodal action distributions. Simulation results show that SAC-CVAE outperforms non-jamming and traditional DRL baselines in secrecy rate and energy efficiency, demonstrating its practicality for secure low-altitude maritime networks with dynamic eavesdroppers.

Abstract

Low-altitude wireless networks (LAWNs) have emerged as a viable solution for maritime communications. In these maritime LAWNs, unmanned aerial vehicles (UAVs) serve as practical low-altitude platforms for wireless communications due to their flexibility and ease of deployment. However, the open and clear UAV communication channels make maritime LAWNs vulnerable to eavesdropping attacks. Existing security approaches often assume eavesdroppers follow predefined trajectories, which fails to capture the dynamic movement patterns of eavesdroppers in realistic maritime environments. To address this challenge, we consider a low-altitude maritime communication system that employs intelligent jamming to counter dynamic eavesdroppers with uncertain positioning to enhance the physical layer security. Since such a system requires balancing the conflicting performance metrics of the secrecy rate and energy consumption of UAVs, we formulate a secure and energy-efficient maritime communication multi-objective optimization problem (SEMCMOP). To solve this dynamic and long-term optimization problem, we first reformulate it as a partially observable Markov decision process (POMDP). We then propose a novel soft actor-critic with conditional variational autoencoder (SAC-CVAE) algorithm, which is a deep reinforcement learning algorithm improved by generative artificial intelligence. Specifically, the SAC-CVAE algorithm employs advantage-conditioned latent representations to disentangle and optimize policies, while enhancing computational efficiency by reducing the state space dimension. Simulation results demonstrate that our proposed intelligent jamming approach achieves secure and energy-efficient maritime communications.

Figures (10)

• Figure 1: A low-altitude maritime communication system with dynamic and uncertain eavesdropper positioning.
• Figure 2: The architecture of the proposed SAC-CVAE algorithm for solving the SEMCMOP, which integrates a CVAE-based improved framework to disentangle and optimize policies as well as an LSTM-assisted prediction mechanism to enhance computational efficiency.
• Figure 3: Total secrecy rates obtained by the intelligent jamming and non-jamming approaches as Eve approaches the MU and Eve moves away from the MU.
• Figure 4: The optimization objective values obtained by different algorithms as Eve approaches the MU.
• Figure 5: The optimization objective values obtained by different algorithms as Eve moves away from the MU.