Title :

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

Author(s) :

Truong, H. T. [Auteur]
Ta, B. P. [Auteur]
Le, Q. A. [Auteur]
Nguyen, D. M. [Auteur]
Le, C. T. [Auteur]
Nguyen, H. X. [Auteur]
Do, H. [Auteur]
Nguyen, H. T. [Auteur]
Tran, Kim-Phuc [Auteur]
Génie des Matériaux Textiles - ULR 2461 [GEMTEX]

Journal title :

Computers in Industry

Abbreviated title :

Comput. Ind.

Volume number :

140

Publication date :

2022-09

ISSN :

0166-3615

English keyword(s) :

Anomaly detection
ICS
Federated learning
Autoencoder
Transformer
Fourier

HAL domain(s) :

Sciences de l'ingénieur [physics]

English abstract : [en]

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 ...
Show more >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.Show less >

Language :

Anglais

Audience :

Internationale

Popular science :

Non

Administrative institution(s) :

Université de Lille
ENSAIT
Junia HEI

Collections :

• Génie des matériaux textiles (GEMTEX) - ULR 2641

Submission date :

2023-06-20T12:04:34Z
2024-02-21T16:13:21Z