Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GAN-based Generator of Adversarial Attack on Intelligent End-to-End Autoencoder-based Communication System

Jianyuan Chen, Lin Zhang, Zuwei Chen, Yawen Chen, Hongcheng Zhuang

TL;DR

This work addresses security vulnerabilities of intelligent end-to-end autoencoder communications by introducing a GAN-based perturbation generator that operates without target information. By employing a Wasserstein-distance–driven training framework, the perturbation generator produces input-agnostic perturbations that markedly degrade block error rate across AWGN, Rayleigh, and high-speed railway channels, while maintaining low detectability. The approach demonstrates superior attack performance compared with several baselines and delivers fast perturbation generation, enabling practical real-time deployment. The findings underscore the need for robust defenses against adversarial perturbations in neural-assisted wireless systems and highlight the practical impact for secure design of future intelligent communication networks.

Abstract

Deep neural networks have been applied in wireless communications system to intelligently adapt to dynamically changing channel conditions, while the users are still under the threat of the malicious attacks due to the broadcasting property of wireless channels. However, most attack models require the knowledge of the target details, which is difficult to be implemented in real systems. Our objective is to develop an attack model with no requirement for the target information, while enhancing the block error rate. In our design, we propose a novel Generative Adversarial Networks(GANs) based attack architecture, which exploits the property of deep learning models being vulnerable to perturbations induced by dynamically changing channel conditions. In the proposed generator, the attack network is composed of convolution layer, convolution transpose layer and linear layer. Then we present the training strategy and the details of the training algorithm. Subsequently, we propose the validation strategy to evaluate the performance of the generator. Simulations are conducted and the results show that our proposed adversarial attack generator achieve better block error rate attack performance than that of benchmark schemes over Additive White Gaussian Noise (AWGN) channel, Rayleigh channel and High-Speed Railway channel.

GAN-based Generator of Adversarial Attack on Intelligent End-to-End Autoencoder-based Communication System

TL;DR

This work addresses security vulnerabilities of intelligent end-to-end autoencoder communications by introducing a GAN-based perturbation generator that operates without target information. By employing a Wasserstein-distance–driven training framework, the perturbation generator produces input-agnostic perturbations that markedly degrade block error rate across AWGN, Rayleigh, and high-speed railway channels, while maintaining low detectability. The approach demonstrates superior attack performance compared with several baselines and delivers fast perturbation generation, enabling practical real-time deployment. The findings underscore the need for robust defenses against adversarial perturbations in neural-assisted wireless systems and highlight the practical impact for secure design of future intelligent communication networks.

Abstract

Deep neural networks have been applied in wireless communications system to intelligently adapt to dynamically changing channel conditions, while the users are still under the threat of the malicious attacks due to the broadcasting property of wireless channels. However, most attack models require the knowledge of the target details, which is difficult to be implemented in real systems. Our objective is to develop an attack model with no requirement for the target information, while enhancing the block error rate. In our design, we propose a novel Generative Adversarial Networks(GANs) based attack architecture, which exploits the property of deep learning models being vulnerable to perturbations induced by dynamically changing channel conditions. In the proposed generator, the attack network is composed of convolution layer, convolution transpose layer and linear layer. Then we present the training strategy and the details of the training algorithm. Subsequently, we propose the validation strategy to evaluate the performance of the generator. Simulations are conducted and the results show that our proposed adversarial attack generator achieve better block error rate attack performance than that of benchmark schemes over Additive White Gaussian Noise (AWGN) channel, Rayleigh channel and High-Speed Railway channel.
Paper Structure (19 sections, 12 equations, 16 figures, 4 tables, 2 algorithms)

This paper contains 19 sections, 12 equations, 16 figures, 4 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model
  3. Intelligent end-to-end autoencoder communication system
  4. Channel model
  5. Vulnerability analysis of neural networks
  6. Adversarial perturbation generator
  7. Training framework and algorithm design
  8. Structure of adversarial perturbation generator
  9. Loss function design
  10. Training and validation algorithm
  11. Deployment of attack generator
  12. Simulation Results
  13. Experimental Environment
  14. Parameter settings
  15. Block error rate performance analysis
  16. ...and 4 more sections

Figures (16)

  • Figure 1: Application scenario of the intelligent end-to-end autoencoder-based communication system model
  • Figure 2: Diagram of Data Transmission in High-speed Railway Communication System
  • Figure 3: Attack imposed on intelligent receivers
  • Figure 4: Training framework of adeversarial attack generator
  • Figure 5: Structure of the generator
  • ...and 11 more figures