Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pozdnyakov, Vitaliy, Kovalenko, Aleksandr, Makarov, Ilya, Drobyshevskiy, Mikhail, Lukyanov, Kirill
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909218979708928
author Pozdnyakov, Vitaliy
Kovalenko, Aleksandr
Makarov, Ilya
Drobyshevskiy, Mikhail
Lukyanov, Kirill
author_facet Pozdnyakov, Vitaliy
Kovalenko, Aleksandr
Makarov, Ilya
Drobyshevskiy, Mikhail
Lukyanov, Kirill
contents Integrating machine learning into Automated Control Systems (ACS) enhances decision-making in industrial process management. One of the limitations to the widespread adoption of these technologies in industry is the vulnerability of neural networks to adversarial attacks. This study explores the threats in deploying deep learning models for fault diagnosis in ACS using the Tennessee Eastman Process dataset. By evaluating three neural networks with different architectures, we subject them to six types of adversarial attacks and explore five different defense methods. Our results highlight the strong vulnerability of models to adversarial samples and the varying effectiveness of defense strategies. We also propose a novel protection approach by combining multiple defense methods and demonstrate it's efficacy. This research contributes several insights into securing machine learning within ACS, ensuring robust fault diagnosis in industrial processes.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13502
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process
Pozdnyakov, Vitaliy
Kovalenko, Aleksandr
Makarov, Ilya
Drobyshevskiy, Mikhail
Lukyanov, Kirill
Machine Learning
Cryptography and Security
Systems and Control
I.2.6; I.2.1
Integrating machine learning into Automated Control Systems (ACS) enhances decision-making in industrial process management. One of the limitations to the widespread adoption of these technologies in industry is the vulnerability of neural networks to adversarial attacks. This study explores the threats in deploying deep learning models for fault diagnosis in ACS using the Tennessee Eastman Process dataset. By evaluating three neural networks with different architectures, we subject them to six types of adversarial attacks and explore five different defense methods. Our results highlight the strong vulnerability of models to adversarial samples and the varying effectiveness of defense strategies. We also propose a novel protection approach by combining multiple defense methods and demonstrate it's efficacy. This research contributes several insights into securing machine learning within ACS, ensuring robust fault diagnosis in industrial processes.
title Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process
topic Machine Learning
Cryptography and Security
Systems and Control
I.2.6; I.2.1
url https://arxiv.org/abs/2403.13502