Multi-Agent SAC Enabled Beamforming Design for Joint Secret Key Generation and Data Transmission

TL;DR

This paper introduces a multi-agent SAC-based beamforming method for joint secret key generation and data transmission in TDD systems, improving security and rates amid eavesdropping threats.

Contribution

It develops a novel multi-agent reinforcement learning framework with LSTM for secure beamforming, addressing nonconvex optimization and partial eavesdropper observability.

Findings

Outperforms benchmark algorithms in key rate and data throughput

Effectively balances secret key generation and data transmission

Robust against intelligent eavesdroppers and partial observations

Abstract

Physical layer key generation (PLKG) has emerged as a promising solution for achieving highly secured and low-latency key distribution, offering information-theoretic security that is inherently resilient to quantum attacks. However, simultaneously ensuring a high data transmission rate and a high secret key generation rate under eavesdropping attacks remains a major challenge. In time-division duplex (TDD) systems with multiple antennas, we derive closed-form expressions for both rates by modeling the legitimate channel as a time-correlated autoregressive (AR) process. This formulation leads to a highly nonconvex and time-coupled optimization problem, rendering traditional optimization methods ineffective. To address this issue, we propose a multi-agent soft actor-critic (SAC) framework equipped with a long short-term memory (LSTM) adversary prediction module to cope with the partial observability of the eavesdropper's mode. Simulation results demonstrate that the proposed approach achieves superior performance compared with other benchmark algorithms, while effectively balancing the trade-off between secret key generation rate and data transmission rate. The results also confirm the robustness of the proposed framework against intelligent eavesdropping and partial observation uncertainty.