THE IMPACT OF AI ON OT CYBERSECURITY

Peter HUNORFI, Alexandru BABOȘ

Abstract


OT systems are interconnected with IT networks and cloud services, which increases their exposure to cyber threats. AI is rapidly being integrated into intrusion detection systems, threat intelligence and risk management workflows. This study is based on academic literature, industrial case studies and OT-specific threat reports to analyse how AI is changing OT cybersecurity. The paper examines AI enabled offensive capabilities, such as AI enhanced malware, AI optimized denial-of-service, data exposure, HMI manipulation, power analysis and RF technology, timing-based and side channel attacks. These attack classes are mapped to corresponding defence strategies. The reviewed literature reports improved detection accuracy and response efficiency in OT environments, but simultaneously introduces new attack surfaces, data-quality dependencies and model-transparency issues. The study concludes that AI should be deployed as an additional, carefully governed analytical layer on top of robust OT security architectures, segmented network design, and human oversight.

Full Text:

PDF

References


Dragos, 2025 OT/ICS Cybersecurity Report. 2025.

M. Keshk, E. Sitnikova, N. Moustafa, J. Hu, and I. Khalil, An Integrated Framework for Privacy-Preserving Based Anomaly Detection for Cyber-Physical Systems, 2021, doi: 10.1109/TSUSC.2019.2906657.

L. Deng, X. Zhang, Q. Zheng, D. Zhao, J. Zhou, and J. Xiang, A New Dataset for Intrusion Detection in Industrial Control System - A Gas Pipeline Testbed Study, 2023, doi: 10.1109/ISPA-BDCloud-SocialCom-SustainCom59178.2023.00149.

A. Abid, F. Jemili, and O. Korbaa, Real-Time Data Fusion for Intrusion Detection in Industrial Control Systems Based on Cloud Computing and Big Data Techniques, 2024, doi: 10.1007/s10586-023-04087-7.

H. Karimipour and F. Derakhshan, Artificial Intelligence for Threat Detection and Analysis in Industrial IoT - Applications and Challenges, 2021, doi: 10.1007/978-3-030-76613-9_1.

D. A. Yeager et al., Case Study- Architecting a Solution to Detect Industrial Control System Attacks, 2020, doi: 10.1109/SSS47320.2020.9197724.

E. Amer and T. Elboghdadly, Evaluating Machine Learning Techniques for ICS Security - Insights from Dataset Limitations and Classifier Performance, 2024, doi: 10.1109/MIUCC62295.2024.10783517.

H. da Conceição Aberto, J. M. Dembele, I. DIop, and A. Bah, Review of Intrusion Detection Systems for Supervisor Control and Data Acquisition - A Machine Learning Approach, 2024, doi: 10.1007/978-3-031-72287-5_3.

B. S. Ali et al., ICS-IDS-Application of Big Data Analysis in AI-based Intrusion Detection Systems to Identify Cyberattacks in ICS Networks, 2024, doi: 10.1007/s11227-023-05764-5.

A. Howe and M. Papa, Feature Engineering in Machine Learning-Based Intrusion Detection Systems for OT Networks, 2023, doi: 10.1109/SMARTCOMP58114.2023.00086.

I. Khan, D. Pi, Z. Khan, Y. Hussain, and A. Nawaz, HML-IDS: A Hybrid-Multilevel Anomaly Prediction Approach for Intrusion Detection in SCADA Systems, IEEE Access, vol. PP, pp. 1-1, July 2019, doi: 10.1109/ACCESS.2019.2925838.

O. Polat, A. Ayid Ahmad, S. Oyucu, E. Algül, F. Doğan, and A. Aksöz, Temporal-Spatial Feature Extraction in IoT-Based SCADA System Security-Hybrid CNN-LSTM and Attention-Based Architectures for Malware Classification and Attack Detection, 2025, doi: 10.1109/ACCESS.2025.3577761.

P. Radoglou-Grammatikis et al., SPEAR SIEM - A Security Information and Event Management system for the Smart Grid, 2021, doi: 10.1016/j.comnet.2021.108008.

J. Bertholat, M. Merad, J. Barbier, and J. Clerc, Practical Use Of AI For Cyber Risk Management In Critical Infrastructures - A Review, 2024.

C. V. S. Suresh Babu, S. Manoharan, and P. A. Simon, Cybersecurity for AI-Enhanced Supervisory Control and Data Acquisition (SCADA) Systems - Safeguarding Critical Infrastructure from Evolving Cyber Threats, 2025, doi: 10.4018/979-8-3373-0583-7.ch010.

N. Papernot, P. McDaniel, S. Jha, M. Fredrikson, Z. B. Celik, and A. Swami, The Limitations of Deep Learning in Adversarial Settings. 2016, p. 387. doi: 10.1109/EuroSP.2016.36.

E. Hodo, X. Bellekens, A. Hamilton, P. Dubouilh, E. Iorkyase, and C. Tachtatzis, Threat Analysis of IoT Networks Using Artificial Neural Network Intrusion Detection System. 2017. doi: 10.48550/arXiv.1704.02286.

Blackfog, The State of Ransomware 2024. 2024. [Online]. Available: https://www.blackfog.com/the-state-of-ransomware-2024/

F. B. Saghezchi, G. Mantas, M. A. Violas, A. M. Manuel De Oliveira Duarte, and J. Rodriguez, Machine Learning for DDoS Attack Detection in Industry 4.0 CPPSs, 2022, doi: 10.3390/electronics11040602.

V. Ya. Ushakov, I. U. Rakhmonov, A. B. Askarov, and D. S. Nikitin, Digitalization of Electrical Power Engineering - Scientific and Technical Fundamentals and Achieved Advantages, 2025, doi: 10.1007/978-3-031-95705-5.

A. Javadpour, F. Ja’fari, T. Taleb, M. Shojafar, and C. Benzaïd, A Comprehensive Survey on Cyber Deception Techniques To Improve Honeypot Performance, Computers & Security, vol. 140, p. 103792, May 2024, doi: 10.1016/j.cose.2024.103792.

J. Squillace, J. Cappella, and A. Sepp, User Vulnerabilities in AI-Driven Systems- Current Cybersecurity Threat Dynamics and Malicious Exploits in Supply Chain Management and Project Management, 2024, doi: 10.1109/ICETSIS61505.2024.10459480.

C. Gangadhar, R. G. Mapari, A. K. Muthevi, A. Suneetha, S. K. B V, and B. Mouleswararao, Exploring the Role of Behavioral Analytics and Anomaly Detection in Securing Mobile Networks for Critical Infrastructure, 2025, doi: 10.1080/19393555.2025.2479027.

R. Benadjila, E. Prouff, R. Strullu, E. Cagli, and C. Dumas, Deep Learning for Side-channel Analysis and Introduction to ASCAD Database, Journal of Cryptographic Engineering, vol. 10, June 2020, doi: 10.1007/s13389-019-00220-8.

S. D. D. Duque Anton, A. P. Lohfink, and H. D. Schotten, Discussing the Feasibility of Acoustic Sensors for Side Channel-aided Industrial Intrusion Detection - An Essay, 2019, doi: 10.1145/3360664.3360667.

A. Flatscher, B. Stojanović, and O. Özdenizci, Enhancing Adversarial Robustness of Anomaly Detection-Based IDS in OT Environments, 2024, doi: 10.23919/CNSM62983.2024.10814511.

A. Aruna et al., Hybrid Deep Learning Approaches for Cyberattack Detection and Prevention in Critical Infrastructure Systems, 2025.

M. Barbhaya, P. R. Dasari, S. K. Damarla, R. Srinivasan, and B. Huang, A Deep Learning Framework for Cyberattack Detection and Classification in Industrial Control Systems, 2025, doi: 10.1016/j.compchemeng.2025.109278.

U. J. Otokwala and A. Petrovski, Ensemble Common Features Technique for Lightweight Intrusion Detection in Industrial Control System, 2023, doi: 10.1109/ICPS58381.2023.10128040.

T. Gebremichael et al., Security and Privacy in the Industrial Internet of Things: Current Standards and Future Challenges, IEEE Access, vol. PP, pp. 1–1, Aug. 2020, doi: 10.1109/ACCESS.2020.3016937.


Refbacks

  • There are currently no refbacks.


JOURNAL INDEXED IN :