Convolutional Neural Network and Deep One-Class Support Vector Machine with Imbalanced Dataset for Anomaly Network Traffic Detection

Anomaly detection of network traffic is important for real-time network monitoring and management. The research challenges for anomaly network traffic detection (ANTD) are attributable to the nature of highly imbalanced dataset of abnormal samples and poor generalization. Generating additional training data or undersampling does not perform well with highly imbalanced dataset. The drives to the common formulation of ANTD as an one-class classification problem. Convolution neural network is utilized for feature extraction. This is followed by a deep one-class support vector machine classifier with customized kernel via multiple kernel learning to address the issue of generalization and overfitting. The deep architecture leverages the performance of traditional support vector machine to a large extent. Performance evaluation reveals that the proposed algorithm achieves accuracy of 97.5%. Ablation studies show that our algorithm enhances the accuracy by 2.52–15.2%. Compared with existing work, our algorithm enhances the accuracy by 3.07%. Several future research directions are discussed for further exploration and analysis.