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.
Shuang WANG
Evaluation Center of Civil Aviation University of China
Hui CHEN
Civil Aviation University of China
Lei DING
Guangzhou University
He SUI
Civil Aviation University of China
Jianli DING
Civil Aviation University of China
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Shuang WANG, Hui CHEN, Lei DING, He SUI, Jianli DING, "GAN-SR Anomaly Detection Model Based on Imbalanced Data" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 7, pp. 1209-1218, July 2023, doi: 10.1587/transinf.2022EDP7187.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7187/_p
Copy
@ARTICLE{e106-d_7_1209,
author={Shuang WANG, Hui CHEN, Lei DING, He SUI, Jianli DING, },
journal={IEICE TRANSACTIONS on Information},
title={GAN-SR Anomaly Detection Model Based on Imbalanced Data},
year={2023},
volume={E106-D},
number={7},
pages={1209-1218},
abstract={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.},
keywords={},
doi={10.1587/transinf.2022EDP7187},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - GAN-SR Anomaly Detection Model Based on Imbalanced Data
T2 - IEICE TRANSACTIONS on Information
SP - 1209
EP - 1218
AU - Shuang WANG
AU - Hui CHEN
AU - Lei DING
AU - He SUI
AU - Jianli DING
PY - 2023
DO - 10.1587/transinf.2022EDP7187
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2023
AB - 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.
ER -