Deep Learning-Assisted Jamming Mitigation with Movable Antenna Array

TL;DR

This work addresses anti-jamming for a wireless link under multiple attackers by leveraging a movable antenna array at the receiver. It proposes a deep learning framework that decomposes the problem into a Rayleigh-quotient beamforming subproblem and a neural network–driven antenna-positioning subproblem, trained with stochastic gradient descent for offline learning and fast online inference. The learned policy maps input directions of arrival {θ_k} to a feasible antenna layout {x_n} and beamformer w, maximizing the receive SINR η. The approach yields near-optimal anti-jamming performance with reduced computational burden compared to traditional optimization, highlighting the practical potential of movable antennas for dynamic, secure communications.

Abstract

This paper reveals the potential of movable antennas in enhancing anti-jamming communication. We consider a legitimate communication link in the presence of multiple jammers and propose deploying a movable antenna array at the receiver to combat jamming attacks. We formulate the problem as a signal-to-interference-plus-noise ratio maximization, by jointly optimizing the receive beamforming and antenna element positioning. Due to the non-convexity and multi-fold difficulties from an optimization perspective, we develop a deep learning-based framework where beamforming is tackled as a Rayleigh quotient problem, while antenna positioning is addressed through multi-layer perceptron training. The neural network parameters are optimized using stochastic gradient descent to achieve effective jamming mitigation strategy, featuring offline training with marginal complexity for online inference. Numerical results demonstrate that the proposed approach achieves near-optimal anti-jamming performance thereby significantly improving the efficiency in strategy determination.

Figures (6)

• Figure 1: System model.
• Figure 2: The proposed learning architecture.
• Figure 3: Achieved SINR versus the number of antenna elements.
• Figure 4: Achieved SINR versus normalized region size.
• Figure 5: Achieved SINR versus the number of jammers.