Stealth Signals: Multi-Discriminator GANs for Covert Communications Against Diverse Wardens

TL;DR

This paper introduces a multi-discriminator GAN framework for covert wireless communication, enabling signals to evade detection by multiple diverse wardens while maintaining reliable decoding, thus enhancing security in complex environments.

Contribution

It presents a novel multi-discriminator GAN approach for covert communications that outperforms traditional methods in multi-warden scenarios with moving entities.

Findings

Improved detection evasion in multi-warden environments.

Enhanced bit error rates compared to baseline methods.

Scalability to up to five wardens demonstrated.

Abstract

Covert wireless communications are critical for concealing the existence of any transmission from adversarial wardens, particularly in complex environments with multiple heterogeneous detectors. This paper proposes a novel adversarial AI framework leveraging a multi-discriminator Generative Adversarial Network (GAN) to design signals that evade detection by diverse wardens, while ensuring reliable decoding by the intended receiver. The transmitter is modeled as a generator that produces noise-like signals, while every warden is modeled as an individual discriminator, suggesting varied channel conditions and detection techniques. Unlike traditional methods like spread spectrum or single-discriminator GANs, our approach addresses multi-warden scenarios with moving receiver and wardens, which enhances robustness in urban surveillance, military operations, and 6G networks. Performance evaluation shows encouraging results with improved detection probabilities and bit error rates (BERs), in up to five warden cases, compared to noise injection and single-discriminator baselines. The scalability and flexibility of the system make it a potential candidate for future wireless secure systems, and potential future directions include real-time optimization and synergy with 6G technologies such as intelligent reflecting surfaces.