Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process
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 thr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of the Industrial Electronics Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10531068/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526335366758400 |
|---|---|
| author | Vitaliy Pozdnyakov Aleksandr Kovalenko Ilya Makarov Mikhail Drobyshevskiy Kirill Lukyanov |
| author_facet | Vitaliy Pozdnyakov Aleksandr Kovalenko Ilya Makarov Mikhail Drobyshevskiy Kirill Lukyanov |
| author_sort | Vitaliy Pozdnyakov |
| collection | DOAJ |
| description | 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 Detection and Diagnosis (FDD) 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 new defense strategy based on combining adversarial training and data quantization. This research contributes several insights into securing machine learning within ACS, ensuring robust FDD in industrial processes. |
| format | Article |
| id | doaj-art-330a130fa2e9493184d8aaa83e184505 |
| institution | Kabale University |
| issn | 2644-1284 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Industrial Electronics Society |
| spelling | doaj-art-330a130fa2e9493184d8aaa83e1845052025-01-17T00:00:51ZengIEEEIEEE Open Journal of the Industrial Electronics Society2644-12842024-01-01542844010.1109/OJIES.2024.340139610531068Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman ProcessVitaliy Pozdnyakov0https://orcid.org/0000-0003-4369-4068Aleksandr Kovalenko1https://orcid.org/0000-0003-3562-0472Ilya Makarov2https://orcid.org/0000-0002-3308-8825Mikhail Drobyshevskiy3https://orcid.org/0000-0002-1639-9154Kirill Lukyanov4https://orcid.org/0009-0009-5235-2175AIRI, Moscow, RussiaAIRI, Moscow, RussiaAIRI, Moscow, RussiaISP RAS Research Center for Trusted Artificial Intelligence, Moscow, RussiaISP RAS Research Center for Trusted Artificial Intelligence, Moscow, RussiaIntegrating 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 Detection and Diagnosis (FDD) 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 new defense strategy based on combining adversarial training and data quantization. This research contributes several insights into securing machine learning within ACS, ensuring robust FDD in industrial processes.https://ieeexplore.ieee.org/document/10531068/Adversarial attacksautomated control systems (ACS)defense methodsfault detection and diagnosis (FDD)Tennessee Eastman Process |
| spellingShingle | Vitaliy Pozdnyakov Aleksandr Kovalenko Ilya Makarov Mikhail Drobyshevskiy Kirill Lukyanov Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process IEEE Open Journal of the Industrial Electronics Society Adversarial attacks automated control systems (ACS) defense methods fault detection and diagnosis (FDD) Tennessee Eastman Process |
| title | Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process |
| title_full | Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process |
| title_fullStr | Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process |
| title_full_unstemmed | Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process |
| title_short | Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process |
| title_sort | adversarial attacks and defenses in fault detection and diagnosis a comprehensive benchmark on the tennessee eastman process |
| topic | Adversarial attacks automated control systems (ACS) defense methods fault detection and diagnosis (FDD) Tennessee Eastman Process |
| url | https://ieeexplore.ieee.org/document/10531068/ |
| work_keys_str_mv | AT vitaliypozdnyakov adversarialattacksanddefensesinfaultdetectionanddiagnosisacomprehensivebenchmarkonthetennesseeeastmanprocess AT aleksandrkovalenko adversarialattacksanddefensesinfaultdetectionanddiagnosisacomprehensivebenchmarkonthetennesseeeastmanprocess AT ilyamakarov adversarialattacksanddefensesinfaultdetectionanddiagnosisacomprehensivebenchmarkonthetennesseeeastmanprocess AT mikhaildrobyshevskiy adversarialattacksanddefensesinfaultdetectionanddiagnosisacomprehensivebenchmarkonthetennesseeeastmanprocess AT kirilllukyanov adversarialattacksanddefensesinfaultdetectionanddiagnosisacomprehensivebenchmarkonthetennesseeeastmanprocess |