VAE-GAN-Guided Cross-Class Generation: A Class Imbalance Data Augmentation Method for Network Intrusion Detection
Fuyuan Kang, Tao Feng, Jiaqi Lin
Abstract
Network intrusion datasets often face class imbalance issues in intrusion detection tasks, where the number of majority class samples is much higher than minority class samples. Current solutions face notable limitations: traditional normalization weakens the multimodal distribution of continuous features, while mainstream generative models focus excessively on minority class mining while neglecting majority class information. To address these issues, we propose M2M-VAEGAN, which innovatively incorporates a Variational Gaussian Mixture (VGM) model to preserve multimodal characteristics of continuous features. We design a transfer learning framework, pre-training on majority classes to capture general attack patterns, followed by fine-tuning with balanced batches of majority and minority samples to prevent catastrophic forgetting. Additionally, we enhance the VAEGAN architecture with an auxiliary classifier to strengthen conditional information learning. On the NSL-KDD and CIC-IDS2017 datasets, M2M-VAEGAN outperforms methods such as SMOTE, CTGAN, and CTABGAN, achieving a 1.25% to 6.42% improvement in minority class recall. These results demonstrate the effectiveness of the proposed approach.