Search papers, labs, and topics across Lattice.
The paper introduces GMA-SAWGAN-GP, a novel GAN-based data augmentation framework for Intrusion Detection Systems (IDS), designed to improve generalization to unseen attacks. The generator uses Gumbel-Softmax regularization for discrete fields and a self-attention mechanism to capture feature dependencies, while an autoencoder and gating network enhance stability and balance losses. Experiments across three datasets (NSL-KDD, UNSW-NB15, and CICIDS2017) show that IDS models trained on GMA-SAWGAN-GP augmented data achieve significantly higher AUROC and True Positive Rate in Leave-One-Attack-type-Out evaluations, demonstrating improved robustness against unknown attacks.
Augmenting IDS training data with a novel GAN framework boosts detection of unseen network attacks by nearly 4% AUROC, suggesting a promising path to more robust security systems.
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) evaluations using Area Under the Receiver Operating Characteristic (AUROC) and True Positive Rate at a 5 percent False Positive Rate confirm that IDS models trained on augmented datasets achieve higher robustness under unseen attack scenarios. Ablation studies validate the contribution of each component to performance gains. Compared with baseline models, the proposed framework improves binary classification accuracy by an average of 5.3 percent and multi-classification accuracy by 2.2 percent, while AUROC and True Positive Rate at a 5 percent False Positive Rate for unknown attacks increase by 3.9 percent and 4.8 percent, respectively, across the three datasets. Overall, GMA-SAWGAN-GP provides an effective approach to generative augmentation for mixed-type network traffic, improving IDS accuracy and resilience.
