Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 65 references that are in the map. First posted on arXiv 20 Mar 2024.
Builds on
20 of 65 references.
References · 20
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
- 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2017Evasion Attacks against Machine Learning at Test Timecited by 686
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
- 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
- 2019Scaleable input gradient regularization for adversarial robustnesscited by 45
8 more
- 2022Data Poisoning Attacks Against Multimodal Encoderscited by 41
- 2018Gradient Adversarial Training of Neural Networkscited by 17
- 2018SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applicationscited by 12
- 2022Conflicting Interactions Among Protection Mechanisms for Machine Learning Modelscited by 12
- 2021DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networkscited by 10
- 2019Adversarial Attacks on Time-Series Intrusion Detection for Industrial Control Systemscited by 7
- 2023Data-Free Hard-Label Robustness Stealing Attackcited by 6
- 2023An Incremental Gray-box Physical Adversarial Attack on Neural Network Trainingcited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.