Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Fairness-Aware Strategy for B5G Physical-layer Security Leveraging Reconfigurable Intelligent Surfaces

Alex Pierron, Michel Barbeau, Luca De Cicco, Jose Rubio-Hernan, Joaquin Garcia-Alfaro

TL;DR

The paper tackles fairness in DRL-enabled RIS-assisted physical-layer security for multi-user duplex links. It identifies fairness imbalances in prior RL-based security approaches and introduces two fairness-aware reward functions, one minimax (R_fm) and one smooth (R_fs), to balance secrecy with equitable user experience. Through simulations, it shows that fairness-oriented rewards substantially improve the Jain fairness index (near 0.9) and reduce information leakage to eavesdroppers, albeit with some sacrifice in total capacity. The work provides open-source code and datasets to advance research and highlights practical directions for generalization, hardware considerations, and dynamic scenarios. The findings demonstrate that carefully designed reward structures can enable secure and fair RIS-assisted communications in next-generation networks.

Abstract

Reconfigurable Intelligent Surfaces are composed of physical elements that can dynamically alter electromagnetic wave properties to enhance beamforming and lead to improvements in areas with low coverage properties. When combined with Reinforcement Learning techniques, they have the potential to enhance both system behavior and physical-layer security hardening. In addition to security improvements, it is crucial to consider the concept of fair communication. Reconfigurable Intelligent Surfaces must ensure that User Equipment units receive their signals with adequate strength, without other units being deprived of service due to insufficient power. In this paper, we address such a problem. We explore the fairness properties of previous work and propose a novel method that aims at obtaining both an efficient and fair duplex Reconfigurable Intelligent Surface-Reinforcement Learning system for multiple legitimate User Equipment units without reducing the level of achieved physical-layer security hardening. In terms of contributions, we uncover a fairness imbalance of a previous physical-layer security hardening solution, validate our findings and report experimental work via simulation results. We also provide an alternative reward strategy to solve the uncovered problems and release both code and datasets to foster further research in the topics of this paper.

A Fairness-Aware Strategy for B5G Physical-layer Security Leveraging Reconfigurable Intelligent Surfaces

TL;DR

The paper tackles fairness in DRL-enabled RIS-assisted physical-layer security for multi-user duplex links. It identifies fairness imbalances in prior RL-based security approaches and introduces two fairness-aware reward functions, one minimax (R_fm) and one smooth (R_fs), to balance secrecy with equitable user experience. Through simulations, it shows that fairness-oriented rewards substantially improve the Jain fairness index (near 0.9) and reduce information leakage to eavesdroppers, albeit with some sacrifice in total capacity. The work provides open-source code and datasets to advance research and highlights practical directions for generalization, hardware considerations, and dynamic scenarios. The findings demonstrate that carefully designed reward structures can enable secure and fair RIS-assisted communications in next-generation networks.

Abstract

Reconfigurable Intelligent Surfaces are composed of physical elements that can dynamically alter electromagnetic wave properties to enhance beamforming and lead to improvements in areas with low coverage properties. When combined with Reinforcement Learning techniques, they have the potential to enhance both system behavior and physical-layer security hardening. In addition to security improvements, it is crucial to consider the concept of fair communication. Reconfigurable Intelligent Surfaces must ensure that User Equipment units receive their signals with adequate strength, without other units being deprived of service due to insufficient power. In this paper, we address such a problem. We explore the fairness properties of previous work and propose a novel method that aims at obtaining both an efficient and fair duplex Reconfigurable Intelligent Surface-Reinforcement Learning system for multiple legitimate User Equipment units without reducing the level of achieved physical-layer security hardening. In terms of contributions, we uncover a fairness imbalance of a previous physical-layer security hardening solution, validate our findings and report experimental work via simulation results. We also provide an alternative reward strategy to solve the uncovered problems and release both code and datasets to foster further research in the topics of this paper.

Paper Structure

This paper contains 20 sections, 15 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Reconfigurable Intelligent Surfaces
  4. Deep Reinforcement Learning
  5. Related Work
  6. System Considered and Problem Statement
  7. Physical-layer Model
  8. Threat Model
  9. Controller Model
  10. Problem Formulation
  11. Fairness Model
  12. Reward Functions and Fairness Improvements
  13. Quality-of-Service-Aware Reward Function
  14. Fairness-aware Reward Function
  15. Experimental Framework and Results
  16. ...and 5 more sections

Figures (5)

  • Figure 1: General Actor–Critic architecture employed in ddpg.
  • Figure 2: Considered ris-drl environment with multiple ue and eavesdroppers.
  • Figure 3: Evolution of system capacity with respect to the baseline reward in Scenarios 1--3. Each plot represents the baseline reward over time (local average) in Bps/Hz. Results are smoothed with a rolling window of size $500$.
  • Figure 4: Evolution of Jain Fairness Index (jfi) in Scenarios 1--3. Each plot represents user JFI over time (local average). Results are smoothed with a rolling window of size $500$.
  • Figure 5: Eavesdroppers' rewards with respect to the baseline reward in Scenarios 2 and 3. Each plot represents the eavesdropper reward over time (local average) in Bps/Hz. Results are smoothed with a rolling window of size $500$.