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

2025-05-01

AI Summary

End-to-end learned autoencoder-based communication systems are vulnerable to adversarial attacks in broadcast channels; however, existing attack methods rely heavily on prior knowledge of the target model, limiting their practical deployability. Method: This paper proposes a black-box adversarial attack framework requiring no information about the target model. We introduce the first channel-aware generative adversarial network (GAN) architecture tailored for wireless communication autoencoders, integrating convolutional and transposed convolutional layers, and design a dynamic channel perturbation–based adversarial training algorithm. Additionally, we propose joint training and generalization validation across AWGN, Rayleigh, and high-speed railway fading channels. Results: Experiments demonstrate significant BLER degradation across all three channel types, outperforming baseline attacks. The method exhibits strong cross-channel generalization and practical feasibility for real-world deployment.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Develop target-agnostic attack model for wireless systems
• Enhance block error rate using GAN-based adversarial attacks
• Exploit deep learning vulnerability to dynamic channel perturbations

Innovation

• GAN-based attack model without target details
• Convolution and transpose layers in generator
• Validated over multiple channel conditions