Network intrusion detection systems (NIDS) are critical for maintaining the security and integrity of modern networks. Traditional IDS techniques, while effective, often struggle with the evolving nature of cyber threats and the need for real-time detection. This paper proposes WASAE-NIDS, a deep learning-based NIDS that leverages a generative adversarial network (GAN)-assisted conditional autoencoder combined with reverse-frequency class weighting to enhance detection, particularly under severe class imbalance. In evaluating NIDS benchmark datasets, our method demonstrates superior performance in detecting various types of cyber threats with high accuracy and improved performance on minority classes. The results demonstrate the potential of combining GAN-assisted representation learning and class weighting to improve NIDS robustness and effectiveness.
Fu et al. (Sun,) studied this question.