산업제어시스템의 이상 탐지 성능 개선을 위한 데이터 보정 방안 연구
Research on Data Tuning Methods to Improve the Anomaly Detection Performance of Industrial Control Systems
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
머신러닝과 딥러닝의 기술이 보편화되면서 산업제어시스템의 이상(비정상) 탐지 연구에도 적용이 되기 시작하였다. 국내에서는 산업제어시스템의 이상 탐지를 위한 인공지능 연구를 활성화시키기 위하여 HAI 데이터셋을 개발하여 공개하였고, 산업제어시스템 보안위협 탐지 AI 경진대회를 시행하고 있다. 이상 탐지 연구들은 대개 기존의 딥러닝 학습 알고리즘을 변형하거나 다른 알고리즘과 함께 적용하는 앙상블 학습 모델의 방법을 통해 향상된 성능의 학습 모델을 만드는 연구가 대부분 이었다. 본 연구에서는 학습 모델과 데이터 전처리(pre-processing)의 개선을 통한 방법이 아니라, 비정상 데이터를 탐지하여 라벨링 한 결과를 보정하는 후처리(post-processing) 방법으로 이상 탐지의 성능을 개선시키는 연구를 진행하였고, 그 결과 기존 모델의 이상 탐지 성능 대비 약 10% 이상의 향상된 결과를 확인하였다.
Abstract
As the technology of machine learning and deep learning became common, it began to be applied to research on anomaly(abnormal) detection of industrial control systems. In Korea, the HAI dataset was developed and published to activate artificial intelligence research for abnormal detection of industrial control systems, and an AI contest for detecting industrial control system security threats is being conducted. Most of the anomaly detection studies have been to create a learning model with improved performance through the ensemble model method, which is applied either by modifying the existing deep learning algorithm or by applying it together with other algorithms. In this study, a study was conducted to improve the performance of anomaly detection with a post-processing method that detects abnormal data and corrects the labeling results, rather than the learning algorithm and data pre-processing process. Results It was confirmed that the results were improved by about 10% or more compared to the anomaly detection performance of the existing model.
참고문헌 (26)
- Shalyga, "Anomaly detection for water treatment system based on neural network with automatic architecture optimization", arXiv preprint arXiv:1807.07282, ~ (2018)
- Xu, Jiehui, "Anomaly transformer: Time series anomaly detection with association discrepancy", arXiv preprint arXiv:2110. 02642, ~ (2021)
- Blázquez-García, Ane, "A review on outlier", anomaly detection in time series data, 2021, pp.54(3), 1~33
- Braei, Mohammad, "Anomaly detection in univariate time-series: A survey on the state-of-the-art", arXiv preprint arXiv:2004.00433, ~ (2020)
- Filonov, Pavel, "Multivariate industrial time series with cyberattack simulation: Fault detection using an lstm-based predictive data model", arXiv preprint arXiv:1612. 06676, ~ (2016)
- Shin, Hyeok-Ki, "HAI 1. 0 : HIL-based Augmented ICS Security Dataset", 13th USENIX Workshop on Cyber Security Experimentation and Test (CSET 20) (2020)
- "HAI v3.0(22.04), hai dataset technical details v3.0"[URL]
- Hwang, Won-Seok, "Do you know existing accuracy metrics overrate time-series anomaly detections?", Proceedings of the 37th ACM, 2022, ~
- Audibert, Julien, "Usad:Unsupervised anomaly detection on multivariate time series", Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2020)
- Choi, Seungoh, "A comparison of ICS datasets for security research based on attack paths", International Conference on Critical Information Infrastructures Security (2018), Springer
- Lee, Jong-Hu, "Industrial Control System Security Requirements Standard Introduction", TTA, ~ (2017)
- "ICS security dataset" (2022)[URL]
- "Industrial Control Systems Security Threat Detection AI Competition"[URL]
- "Swat datasets"[URL]
- "Industrial control system (ics) cyber attack datasets"[URL]
- "Scada network datasets"[URL]
- "S7comm datasets"[URL]
- "data sciense wiki - an omaly detection"[URL]
- Mahesh, Batta, "Machine learning algorithms-a review", International Journal of Science and Research (IJSR), 9, pp.381~386 (2020)
- "DATA SCIENCE BLOG" (2018)[URL]
- Xingchao Bian, "Detecting Anomalies in Time-Series Data using Unsupervised Learning and Analysis on Infrequent", 전기전자학회논문지, 24(4), pp.1011~1016 (2020), 한국전기전자학회[DOI]
- Bae, Sungho, "Research on Improvement of Anomaly Detection Performance in Industrial Control Systems", International Conference on Information Security Applications (2021), Springer
- Seong, ChangMin, "Towards Building Intrusion Detection Systems for Multivariate Time-Series Data", Silicon Valley Cybersecurity Conference (2021), Springer
- 김효석, "산업제어시스템에서 앙상블 순환신경망 모델을 이용한 비정상 탐지", 정보보호학회논문지, 31(3), pp.401~410 (2021), 한국정보보호학회[DOI]
- Kim, Doyeon, "Stacked-autoencoder based anomaly detection with industrial control system", International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel, 2021, ~[DOI]
- "DACON"[URL]