Adversarial attacks on anomaly detectors in process systems: A case study on Tennessee Eastman process dataset

Abstract The integration of machine learning (ML) techniques into industrial control systems (ICS) across various industries, including chemical process plants, has revolutionized operational decision‐making by enabling faster and more informed responses. However, ICS are increasingly vulnerable to critical challenges, particularly adversarial attacks and data privacy concerns. Adversarial samples, crafted to exploit weaknesses in ML algorithms, can cause misclassifications or erroneous predictions, often evading detection by operators. Such attacks pose substantial risks to anomaly detection systems within ICS, potentially resulting in financial losses, operational disruptions, infrastructure damage, or threats to human safety. While adversarial attacks have been extensively studied in domains such as image and audio processing, their implications for industrial environments, particularly chemical processes, remain underexplored. Industrial systems heavily depend on anomaly detectors to identify deviations from normal operations, making these systems prime targets for adversarial manipulations. This work aims to address this gap by developing anomaly detection models trained on the benchmark Tennessee Eastman process (TEP) dataset. Adversarial attacks are generated and applied to these anomaly detection models to assess their impact and evaluate the performance of these models.