Accuracy and Security-Guaranteed Participant Selection and Beamforming Design for RIS-Assisted Federated Learning

2025-06-30

AI Summary

To address the high training latency and the trade-off between convergence accuracy and uplink security in reconfigurable intelligent surface (RIS)-assisted federated learning (FL) under eavesdropping threats, this paper proposes a joint optimization framework. It leverages non-participating devices as cooperative jammers to enhance physical-layer security, and jointly optimizes participant selection, bandwidth allocation, and RIS beamforming via a Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to solve the resulting mixed-integer nonlinear programming problem. Unlike conventional FL approaches that decouple resource scheduling from physical-layer security design, our method achieves end-to-end co-optimization driven by both accuracy and security constraints—marking the first such formulation. Simulation results demonstrate that the proposed scheme reduces per-round training latency by 27% compared to baseline methods, significantly improving both training efficiency and communication security.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Security and privacy of machine learning and AI applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Federated learning (FL) has emerged as an effective approach for training neural network models without requiring the sharing of participants' raw data, thereby addressing data privacy concerns. In this paper, we propose a reconfigurable intelligent surface (RIS)-assisted FL framework in the presence of eavesdropping, where partial edge devices are selected to participate in the FL training process. In contrast, the remaining devices serve as cooperative jammers by transmitting jamming signals to disrupt eavesdropping. We aim to minimize the training latency in each FL round by jointly optimizing participant selection, bandwidth allocation, and RIS beamforming design, subject to the convergence accuracy of FL and the secure uploading requirements. To solve the resulting mixed-integer nonlinear programming problem, we propose a twin delayed deep deterministic policy gradient (TD3) algorithm. Simulation results demonstrate that the proposed scheme reduces the FL training latency by approximately 27$%$ compared to baselines.

Problem

• Optimize participant selection and RIS beamforming for secure FL
• Minimize FL training latency under accuracy and security constraints
• Address eavesdropping risks with cooperative jamming in FL systems

Innovation

• RIS-assisted FL framework for secure training
• Joint optimization of selection and beamforming
• TD3 algorithm for minimizing training latency