GAN-SR Anomaly Detection Model Based on Imbalanced Data

• Published in: IEICE Transactions on Information and Systems Vol. E106.D; no. 7; pp. 1209 - 1218
• Main Authors: WANG, Shuang, DING, Jianli, DING, Lei, SUI, He, CHEN, Hui
• Format: Journal Article
• Language: English
• Published: Tokyo The Institute of Electronics, Information and Communication Engineers 01.07.2023; Japan Science and Technology Agency
• Subjects: Anomalies; anomaly detection; Coders; Control systems; Datasets; Decision trees; Feature extraction; GAN; Gas pipelines; Generative adversarial networks; imbalanced datasets; industrial control systems; Industrial electronics; Machine learning; Natural gas; SNDAE; Training
• ISSN: 0916-8532; 1745-1361
• DOI: 10.1587/transinf.2022EDP7187

The issue of a low minority class identification rate caused by data imbalance in anomaly detection tasks is addressed by the proposal of a GAN-SR-based intrusion detection model for industrial control systems. First, to correct the imbalance of minority classes in the dataset, a generative adversarial network (GAN) processes the dataset to reconstruct new minority class training samples accordingly. Second, high-dimensional feature extraction is completed using stacked asymmetric depth self-encoder to address the issues of low reconstruction error and lengthy training times. After that, a random forest (RF) decision tree is built, and intrusion detection is carried out using the features that SNDAE retrieved. According to experimental validation on the UNSW-NB15, SWaT and Gas Pipeline datasets, the GAN-SR model outperforms SNDAE-SVM and SNDAE-KNN in terms of detection performance and stability.