[2603.28838] GMA-SAWGAN-GP: A Novel Data Generative Framework to Enhance IDS Detection Performance

Computer Science > Cryptography and Security arXiv:2603.28838 (cs) [Submitted on 30 Mar 2026] Title:GMA-SAWGAN-GP: A Novel Data Generative Framework to Enhance IDS Detection Performance Authors:Ziyu Mu, Xiyu Shi, Safak Dogan View a PDF of the paper titled GMA-SAWGAN-GP: A Novel Data Generative Framework to Enhance IDS Detection Performance, by Ziyu Mu and 1 other authors View PDF HTML (experimental) Abstract:Intrusion Detection System (IDS) is often calibrated to known attacks and generalizes poorly to unknown threats. This paper proposes GMA-SAWGAN-GP, a novel generative augmentation framework built on a Self-Attention-enhanced Wasserstein GAN with Gradient Penalty (WGAN-GP). The generator employs Gumbel-Softmax regularization to model discrete fields, while a Multilayer Perceptron (MLP)-based AutoEncoder acts as a manifold regularizer. A lightweight gating network adaptively balances adversarial and reconstruction losses via entropy regularization, improving stability and mitigating mode collapse. The self-attention mechanism enables the generator to capture both short- and long-range dependencies among features within each record while preserving categorical semantics through Gumbel-Softmax heads. Extensive experiments on NSL-KDD, UNSW-NB15, and CICIDS2017 using five representative IDS models demonstrate that GMA-SAWGAN-GP significantly improves detection performance on known attacks and enhances generalization to unknown attacks. Leave-One-Attack-type-Out (LOAO) evalua...