<scp>MasqueradeGAN</scp> ‐ <scp>GP</scp> : A Generative Adversarial Network Framework for Evading Black‐Box Intrusion Detection Systems

ABSTRACT The proliferation of sophisticated malware poses an escalating threat to economic and national security, demanding a reevaluation of cybersecurity in next‐generation wireless networks like 6G. Integrating artificial intelligence (AI) offers a crucial opportunity to enhance network defenses against increasingly complex cyber threats. However, the growing complexity of 6G technologies exposes current Intrusion Detection Systems (IDS) to covert malware exploitation, underscoring the need for more adaptive and resilient detection mechanisms. In response to these challenges, this study presents MasqueradeGAN‐GP, an innovative framework based on Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN‐GP). The MasqueradeGAN‐GP framework consists of a generator, responsible for transforming raw malicious traffic into a semblance of benign activity, and a discriminator, which dynamically assimilates the feature set of the IDS to discern between genuine and adversarial traffic. Additionally, it includes a restrictive modification mechanism to ensure the fidelity of attack vectors. Experiments conducted on the CICIDS 2017 and NSL‐KDD datasets indicate that MasqueradeGAN‐GP effectively evades detection, suggesting its potential for advancing IDS capabilities and reinforcing AI‐driven security solutions within the 6G landscape. This contributes to building a more robust detection system capable of facing adversarial malware attacks in future wireless communications.