AAISM materials describe that GAN-based systems excel at generating synthetic data-including simulated attack traffic-which can significantly enhance anomaly-based intrusion detection capabilities. The guidance emphasizes that synthetic attack samples help strengthen the model's ability to detect rare or emerging intrusion types. This aligns with the principle that AI security controls should leverage adversarially generated data during training to improve resilience.
Options A and C describe generic ML enhancements, but not GAN-specific advantages. Option B is useful but insufficient for anomaly detection, which relies heavily on recognizing atypical, previously unseen patterns.
References: AAISM Study Guide - AI Security Controls; Adversarial Simulation and Synthetic Data Generation.