Secure Federated Learning over Wireless Communication Networks with Model Compression

Although federated learning(FL)has become very popular recently,it is vulnerable to gradient leakage attacks.Recent studies have shown that attackers can reconstruct clients’private data from shared models or gradients.Many existing works focus on adding privacy protection mechanisms to prevent user privacy leakages,such as differential privacy(DP)and homomorphic encryption.These defenses may cause an increase in computation and communication costs or degrade the performance of FL.Besides,they do not consider the impact of wireless network resources on the FL training process.Herein,we propose weight compression,a defense method to prevent gradient leakage attacks for FL over wireless networks.The gradient compression matrix is determined by the user’s location and channel conditions.We also add Gaussian noise to the compressed gradients to strengthen the defense.This joint learning of wireless resource allocation and weight compression matrix is formulated as an optimization problem with the objective of minimizing the FL loss function.To find the solution,we first analyze the convergence rate of FL and quantify the effect of the weight matrix on FL convergence.Then,we seek the optimal resource block(RB)allocation by exhaustive search or ant colony optimization(ACO)and then use the CVX toolbox to obtain the optimal weight matrix to minimize the optimization function.The simulation results show that the optimized RB can accelerate the convergence of FL.

Deep Learning for Secure Transmission in Reconfigurable Intelligent Surface-Assisted Communications

This paper investigates the secure transmission for reconfigurable intelligent surface(RIS)-assisted wireless communication systems.In the studied model,one user connects to the access point via a RIS while an eavesdropper eavesdrops on the signal sent from the user to the access point.Therefore,it is necessary to design an appropriate RIS reflection vector to solve the eavesdropping problem.This problem is formulated as an optimization problem whose goal is to maximize the secure energy efficiency which is defined as the ratio of the secure rate to the total energy consumption of the system via jointly optimizing the RIS reflection reflector as well as the number of RIS elements,which results in a non-convex optimization problem that is intractable to solve by traditional methods.To tackle this issue,a new algorithm by leveraging the advance of the established deep learning(DL)technique is proposed so as to find the optimal RIS reflection vector and determine the optimal number of RIS reflection elements.Simulation results show that the proposed method reaches 96%of the optimal secure energy efficiency of the genie-aided algorithm.