Intelligent Disruption: Undetectable Attacks on Wireless Autoencoders

2026-07-21

AI Summary

This work addresses the limitations of conventional adversarial attacks in multi-attacker scenarios, where accumulated perturbations are easily detectable and exhibit unstable performance under dynamic channel conditions. To overcome these challenges, the authors propose an intelligent attack framework that integrates transmit power control with a conditional generative adversarial network (cGAN). By dynamically adjusting transmission power, the framework minimizes interference leakage to enhance stealth, while the cGAN generates perturbation signals that adapt to real-time channel variations, effectively deceiving the receiver’s discriminator. This approach represents the first integration of power control and conditional adversarial generation, achieving a unified balance among high stealth, strong attack efficacy, and environmental adaptability. Extensive simulations demonstrate that the proposed framework significantly outperforms existing baselines in terms of stealthiness, attack strength, and robustness across diverse channel environments.

Abstract

Adversarial attacks can degrade the legitimate decision performance in wireless autoencoder communications. However, in complex scenarios with multiple adversaries, the cumulative leakage interference (CLI) caused by the multiple parallel attacks increases the chance of detecting the attacks, while dynamical environments also make the fixed attack strategies difficult to have stable effectiveness. To jointly enhance the undetectability, aggressivity and adaptability of adversarial attacks, we propose a deep learning based intelligent attack framework. Specifically, considering the CLI caused by the multiple parallel attacks, a deep neural network based transmit power control is established to reduce the interference leakage by regulating the transmit power of these adversaries, thereby improving the undetectability. Furthermore, to enhance the attack effectiveness and stability in the dynamic environment, the conditional generative adversarial attack is further developed. The generator takes the attack channel information as the conditional input to produce the perturbating signals to mislead the discriminator by making the attacked received signals resemble the clean received signals, while the discriminator distinguishes between the two under the same condition. Through the adversarial training, the generator can learn to create adaptive perturbating signals with enhanced attack performance. Simulation results demonstrate that the proposed framework outperforms benchmarks in terms of attack undetectability, aggressivity and adaptability.

Problem

• adversarial attacks
• wireless autoencoders
• cumulative leakage interference
• undetectability
• dynamic environment

Innovation

• intelligent adversarial attack
• cumulative leakage interference
• transmit power control
• conditional generative adversarial network
• wireless autoencoder