CSAGC-IDS: A Dual-Module Deep Learning Network Intrusion Detection Model for Complex and Imbalanced Data

2025-05-20

AI Summary

To address the challenges of high-dimensional, complex, and severely class-imbalanced network traffic data, this paper proposes a dual-module deep learning intrusion detection framework. First, it introduces a self-attention-enhanced convolutional conditional GAN (SC-CGAN), the first to generate high-fidelity minority-class samples for effective imbalance mitigation. Second, it designs a cost-sensitive channel-attention CNN (CSCA-CNN) that jointly incorporates cost-sensitive learning and channel-wise attention to improve detection accuracy and model interpretability. Attribution analysis is further conducted via SHAP and LIME. Evaluated on the NSL-KDD dataset, the framework achieves 84.55% accuracy and F1-score for five-class classification, and 91.09% accuracy and 92.04% F1-score for binary classification—substantially outperforming state-of-the-art methods.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

As computer networks proliferate, the gravity of network intrusions has escalated, emphasizing the criticality of network intrusion detection systems for safeguarding security. While deep learning models have exhibited promising results in intrusion detection, they face challenges in managing high-dimensional, complex traffic patterns and imbalanced data categories. This paper presents CSAGC-IDS, a network intrusion detection model based on deep learning techniques. CSAGC-IDS integrates SC-CGAN, a self-attention-enhanced convolutional conditional generative adversarial network that generates high-quality data to mitigate class imbalance. Furthermore, CSAGC-IDS integrates CSCA-CNN, a convolutional neural network enhanced through cost sensitive learning and channel attention mechanism, to extract features from complex traffic data for precise detection. Experiments conducted on the NSL-KDD dataset. CSAGC-IDS achieves an accuracy of 84.55% and an F1-score of 84.52% in five-class classification task, and an accuracy of 91.09% and an F1 score of 92.04% in binary classification task.Furthermore, this paper provides an interpretability analysis of the proposed model, using SHAP and LIME to explain the decision-making mechanisms of the model.

Problem

• Detects network intrusions in complex, imbalanced data
• Addresses high-dimensional traffic pattern challenges
• Improves detection accuracy using deep learning techniques

Innovation

• Self-attention-enhanced convolutional GAN for data imbalance
• Cost-sensitive CNN with channel attention for feature extraction
• Interpretability analysis using SHAP and LIME techniques