Moving or Predicting? RoleAware-MAPP: A Role-Aware Transformer Framework for Movable Antenna Position Prediction to Secure Wireless Communications

TL;DR

This work addresses the latency and dynamics challenges of movable antenna systems by reframing MA positioning as a predictive task and introducing RoleAware-MAPP, a Transformer-based framework that embeds domain knowledge through role-aware embeddings and physics-informed semantics while optimizing a composite secrecy-focused loss. The model predicts future MA configurations in a non-autoregressive manner, enabling millisecond-scale inference compatible with real-time operation. Empirical results in 3GPP-compliant vehicular scenarios show substantial gains in secrecy rate ($\tilde{R}$) and strictly positive secrecy capacity (SPSC) over diverse speeds and noise conditions, at the cost of higher parameter and FLOP counts. The findings demonstrate practical viability for dynamic PLS with secure MA control and point to future work in hybrid learning approaches and real-world MA testbeds.

Abstract

Movable antenna (MA) technology provides a promising avenue for actively shaping wireless channels through dynamic antenna positioning, thereby enabling electromagnetic radiation reconstruction to enhance physical layer security (PLS). However, its practical deployment is hindered by two major challenges: the high computational complexity of real time optimization and a critical temporal mismatch between slow mechanical movement and rapid channel variations. Although data driven methods have been introduced to alleviate online optimization burdens, they are still constrained by suboptimal training labels derived from conventional solvers or high sample complexity in reinforcement learning. More importantly, existing learning based approaches often overlook communication-specific domain knowledge, particularly the asymmetric roles and adversarial interactions between legitimate users and eavesdroppers, which are fundamental to PLS. To address these issues, this paper reformulates the MA positioning problem as a predictive task and introduces RoleAware-MAPP, a novel Transformer based framework that incorporates domain knowledge through three key components: role-aware embeddings that model user specific intentions, physics-informed semantic features that encapsulate channel propagation characteristics, and a composite loss function that strategically prioritizes secrecy performance over mere geometric accuracy. Extensive simulations under 3GPP-compliant scenarios show that RoleAware-MAPP achieves an average secrecy rate of 0.3569 bps/Hz and a strictly positive secrecy capacity of 81.52%, outperforming the strongest baseline by 48.4% and 5.39 percentage points, respectively, while maintaining robust performance across diverse user velocities and noise conditions.

Figures (10)

• Figure 1: System model of the MA-enabled communication scenario
• Figure 2: The network architecture of proposed model
• Figure 3: Composite loss in training
• Figure 4: SPSC and ASR of proposed model during training
• Figure 5: Comparison of performance metrics between different models