Light-weight federated learning-based anomaly detection for time-series data in industrial control systems

With the emergence of the Industrial Internet of Things (IIoT), potential threats to smart manufacturing systems are increasingly becoming challenging, causing severe damage to production operations and vital industrial assets, even sensitive information. Hence, detecting irregularities for time-ser...

Full description

Saved in:
Bibliographic Details
Published in:Computers in industry 2022-09, Vol.140, p.103692, Article 103692
Main Authors: Truong, Huong Thu, Ta, Bac Phuong, Le, Quang Anh, Nguyen, Dan Minh, Le, Cong Thanh, Nguyen, Hoang Xuan, Do, Ha Thu, Nguyen, Hung Tai, Tran, Kim Phuc
Format: Article
Language:English
Subjects:
Anomaly detection
Artificial Intelligence
Autoencoder
Automatic
Computer Science
Engineering Sciences
Federated learning
Fourier
ICS
Transformer
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the emergence of the Industrial Internet of Things (IIoT), potential threats to smart manufacturing systems are increasingly becoming challenging, causing severe damage to production operations and vital industrial assets, even sensitive information. Hence, detecting irregularities for time-series data in industrial control systems that should operate continually is critical, ensuring security and minimizing maintenance costs. In this study, with the hybrid design of Federated learning, Autoencoder, Transformer, and Fourier mixing sublayer, we propose a robust distributed anomaly detection architecture that works more accurately than several most recent anomaly detection solutions within the ICS contexts, whilst being fast learning in minute time scale. This distributed architecture is also proven to achieve lightweight, consume little CPU and memory usage, have low communication costs in terms of bandwidth consumption, which makes it feasible to be deployed on top of edge devices with limited computing capacity. •A fast-learning model in 20-min time scale that can cope with frequent updating.•A light-weight detection scheme in terms of CPU, Memory usage, and running time.•Faster system response upon attacks since detection is implemented near the sources.•An accurate anomaly detection scheme for time-series data.•Federated learning to reduce bandwidth consumption on the link from Edge to Cloud.
ISSN:0166-3615
1872-6194
DOI:10.1016/j.compind.2022.103692