Adversarial Machine Learning in Critical Infrastructure: A Conceptual Framework for Threat Modeling AI Enabled OT Systems
Abstract
As machine learning components are integrated into operational technology pipelines for predictive maintenance, anomaly detection, demand forecasting, and operator decision support, the attack surface of critical infrastructure expands to include the models themselves. Adversarial machine learning research has demonstrated that classifiers, regressors, and reinforcement learning agents can be deceived, poisoned, or extracted through carefully crafted inputs and training data manipulations. The transfer of these techniques to operational technology contexts is not yet well characterized, in part because the threat model differs from the consumer or vision- based settings in which most adversarial machine learning research originated. This paper proposes a conceptual framework for threat modeling artificial intelligence enabled operational technology systems in critical infrastructure. The framework adapts established threat modeling methods to the unique properties of operational technology, including limited model retraining frequency, narrow sensor and actuator interfaces, deterministic process expectations, and tight integration with human operators. Six threat categories are developed, namely evasion against detection models, data poisoning during model updates, model extraction across vendor boundaries, integrity attacks on inference pipelines, supply chain attacks against pretrained components, and indirect attacks via sensor manipulation. For each category the framework defines adversary objectives, prerequisites, observable indicators, and candidate mitigations. The framework is illustrated through three reference scenarios drawn from power, water, and manufacturing contexts. The paper concludes with a discussion of evaluation strategies, residual gaps, and policy implications, including the need for adversarial robustness expectations within procurement and certification regimes for safety relevant artificial intelligence in critical infrastructure.
Keywords
adversarial machine learning; critical infrastructure; threat modeling; operational technology; artificial intelligence security; conceptual framework.
References
Abdallah, A., Maarof, M.A. and Zainal, A. (2016). Fraud detection system: A survey. Journal of Network and Computer Applications, 68, 90 to 113. Ackerman, P. (2017). Industrial Cybersecurity: Efficiently Secure Critical Infrastructure Systems. Packt Publishing, Birmingham. Adebayo, A. (2020). Wireless internet service provider network reliability frameworks for emerging markets. International Journal of Network and Communication Research, 5(2), 88-103. Tizeti Inc., Nigeria. Adebayo, A. (2021a). Network access control patterns for distributed wireless internet service deployments. International Journal of Information Security Research, 11(4), 215-232. Tizeti Inc., Nigeria. Adebayo, A. (2021b). Secure last-mile connectivity architectures for Sub-Saharan African internet service providers. Journal of African Information Systems, 12(3), 145-162. Tizeti Inc., Nigeria. Adebayo, A. (2022a). Compliance frameworks for financial technology platforms operating across multiple jurisdictions. International Journal of Regulatory Technology, 6(3), 134-152. Squad, Nigeria. Adebayo, A. (2022b). Fintech payment infrastructure security: Threat modeling for high-volume transaction processing platforms. Journal of Financial Technology Security, 8(2), 198-217. Squad, Nigeria. Adepu, S. and Mathur, A. (2016). An investigation into the response of a water treatment system to cyber attacks. HASE 2016, 141 to 148. Adepu, S., Brasser, F., Garcia, L., Rodler, M., Davi, L., Sadeghi, A.R. and Zonouz, S. (2020). Control behavior integrity for distributed cyber physical systems. ACM/IEEE ICCPS 2020. Adesuyi, M. O., Walawalkar, G., & Kalu, A. (2021). Decision-centric financial analytics for executive-level strategy formulation. Journal of Accounting and Financial Management, 7(5), 152 to 173. Adeyoyin, O., Awanye, E. N., Morah, O. O., & Ekpedo, L. (2020). A Conceptual Framework Linking Financial Strategy and Operational Excellence in Manufacturing Firms. Adeyoyin, O., Awanye, E. N., Morah, O. O., & Ekpedo, L. (2021). A Conceptual Framework for Integrating ESG Priorities into Sustainable Corporate Operations. Agbabiaka, J., Okonkwo, C.S., Ogunwole, O., Mayo, W. & Okeke, O.T. (2019). Supply Chain Risk Management Model for EPC and Gas Processing Projects. IRE Journals, 3(2), 968 to 980. DOI: 10.64388/IREV3I2-1713124. Aggarwal, C.C. (2017). Outlier Analysis (2nd ed.). Springer, Cham. Ahmed, M., Mahmood, A.N. and Hu, J. (2016). A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 60, 19 to 31. Ahmed, K.S. & Odejobi, O.D. (2018). Conceptual Framework for Scalable and Secure Cloud Architectures for Enterprise Messaging. IRE Journals, 2(1), 1-15. Ahmed, K. S., Odejobi, O. D., & Oshoba, T. O. (2019). Algorithmic model for constraint satisfaction in cloud network resource allocation. IRE Journals, 2(12). ISSN: 2456-8880. Ahmed, K.S., Odejobi, O.D. & Oshoba, T.O. (2020). Predictive Model for Cloud Resource Scaling Using Machine Learning Techniques. Journal of Frontiers in Multidisciplinary Research, 1(1), 173-183. DOI: 10.54660/.Ijfmr.2020.1.1.173-183. Ahmed, K. S., Odejobi, O. D., & Oshoba, T. O. (2021). Certifying algorithm model for Horn constraint systems in distributed databases. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 7(1), 537-554. Aifuwa, S. E., Oshoba, T. O., Ogbuefi, E., Ike, P. N., Nnabueze, S. B., & Olatunde-Thorpe, J. (2020). Predictive analytics models enhancing supply chain demand forecasting accuracy and reducing inventory management inefficiencies. International Journal of Multidisciplinary Research and Growth Evaluation, 1(3), 171-181. DOI: 10.54660/.IJMRGE.2020.1.3.171-181. Ajayi, A. E., Moyo, T. M., Tafirenyika, S., Taiwo, A. E., Tuboalabo, A., & Bukhari, T. T. (2022). Predictive Analytics Systems for Enhancing Financial Forecast Accuracy and Real-Time Monitoring in Hospital Networks. Akeju, B., Edivri, J., Ogbole, J. I., Okoruwa, P. O., Fadayomi, O., & Abolaji, T. O. (2018). Conceptual model for insider threat classification and risk modeling in complex digital systems. IRE Journals, 1(9). https://doi.org/10.64388/IREV1I9-1713778 Akhtar, N. and Mian, A. (2018). Threat of adversarial attacks on deep learning in computer vision: A survey. IEEE Access, 6, 14410 to 14430. Akin-Oluyomi, O. T., & Akhigbe, R. (2022). A supply chain governance model for enhancing compliance and operational quality across retail networks. All Multidisciplinary Journal. Akinlade, O. F., Filani, O. M., & Nwachukwu, P. S. (2021a). Applied Statistics Models Optimizing Global Supply Chain Networks Under Uncertainty Conditions. Akinlade, O. F., Filani, O. M., & Nwachukwu, P. S. (2021b). Cross-Functional Framework using AI-Enhanced Analysis for Supplier Selection Accuracy. Akinlade, O. F., Filani, O. M., & Nwachukwu, P. S. (2022). Data Visualization with Predictive Modeling Measuring Workplace Diversity Performance Metrics. Akinleye, O. K., & Adeyoyin, O. (2021). Process Automation Framework for Enhancing Procurement Efficiency and Transparency. Akinleye, O. K., & Adeyoyin, O. (2022). Supplier Relationship Management Framework for Achieving Strategic Procurement Objectives. Akinlolu, V. S., Omaghomi, T. T., Fapohunda, M., & Atima, M. E. (2022). A systems-level policy framework for integrating mental health screening into primary healthcare in low-resource settings. Akinola, A. S., Adesanya, O. S., Okafor, C. M., & Farounbi, B. O. (2018). Automated Payroll Compliance Assurance: Linking Withholding Algorithms to Financial Statement Reliability. IRE Journals, 1(7). Akinola, A. S., Farounbi, B. O., Onyelucheya, O. P., & Okafor, C. M. (2020a). Translating finance bills into strategy: Sectoral impact mapping and regulatory scenario analysis. Journal of Frontiers in Multidisciplinary Research, 1(1), 102-111. Akinola, A. S., Okafor, C. M., Dako, O. F., & Adesanya, O. S. (2020b). Evidence-informed Advisory for Ultra-High-Net-Worth Clients: Portfolio Governance and Fiduciary Risk Controls. Journal of Frontiers in Multidisciplinary Research, 1(2), 112-120. Aldaraani, N. and Begum, Z. (2018). Understanding the impact of ransomware: A survey on its evolution, mitigation and prevention techniques. NCC 2018, 1 to 5. Alexander, O., Belisle, M. and Steele, J. (2020). MITRE ATT&CK for Industrial Control Systems: Design and Philosophy. MITRE Corporation, McLean, VA. Alladi, T., Chamola, V. and Zeadally, S. (2020). Industrial control systems: Cyberattack trends and countermeasures. Computer Communications, 155, 1 to 8. Alliance, C. S. (2022). Cloud Controls Matrix v4. Cloud Security Alliance, Seattle, WA. Allodi, L. and Massacci, F. (2014). Comparing vulnerability severity and exploits using case control studies. ACM TISSEC, 17(1), 1 to 20. Almorsy, M., Grundy, J. and Muller, I. (2016). An analysis of the cloud computing security problem. arXiv preprint arXiv:1609.01107. Alsentzer, E., Murphy, J.R., Boag, W., Weng, W.H., Jin, D., Naumann, T. and McDermott, M. (2019). Publicly available clinical BERT embeddings. Proceedings of the 2nd Clinical Natural Language Processing Workshop, 72 to 78. Ambali, K.B., Eyetsemitan, R.A., Oyeleye, A.O. & Fadayomi, O. (2021). Lean Six Sigma for Small Enterprises: A Systematic Review and Lite-DMAIC Adaptation Framework for Resource-Constrained Organizations. IRE Journals, 5(5), 562 to 583. DOI: 10.64388/IREV5I5 to 1716957 Amebleh, J., Igba, E. & Ijiga, O. M. (2021). Graph-Based Fraud Detection in Open-Loop Gift Cards: Heterogeneous GNNs, Streaming Feature Stores, and Near-Zero-Lag Anomaly Alerts International Journal of Scientific Research in Science, Engineering and Technology Volume 8, Issue 6 DOI: https://doi.org/10.32628/IJSRSET214418 Amin, M. and Wollenberg, B.F. (2005). Toward a smart grid: Power delivery for the 21st century. IEEE Power and Energy Magazine, 3(5), 34 to 41. Aminu-Ibrahim, A. Y., Ogbete, J. C., & Ambali, K. B. (2018). Developing sustainable diagnostic laboratory infrastructure models for emerging and resource constrained health systems. Iconic Research and Engineering Journals, 1(8), 118 to 132.https://doi.org/10.64388/IREV1I8 to 1713586 Aminu-Ibrahim, A.Y., Ogbete, J.C. & Ambali, K.B. (2019). Capital Project Delivery Models for High Risk Healthcare Infrastructure in Developing National Health Systems. Iconic Research and Engineering Journals, 2(10), 626 to 649. DOI: 10.64388/IREV2I10 to 1713588. Aminu-Ibrahim, A.Y., Ogbete, J.C. & Ambali, K.B. (2020). Infrastructure Driven Expansion of Diagnostic Access Across Underserved and Rural Healthcare Regions. International Journal of Multidisciplinary Research and Growth Evaluation, 1(5), 691 to 706. DOI: 10.54660/IJMRGE.2020.1.5.691 to 706. Anderson, R. (2008). Security Engineering: A Guide to Building Dependable Distributed Systems (2nd ed.). Wiley, Indianapolis, IN. Ani, U.P.D., He, H. and Tiwari, A. (2017). Review of cybersecurity issues in industrial critical infrastructure: Manufacturing in perspective. Journal of Cyber Security Technology, 1(1), 32 to 74. Anichukwueze, C. C., Osuji, V. C., & Oguntegbe, E. E. (2019). Global marketing law and consumer protection challenges: a strategic framework for multinational compliance. IRE Journals, 3(6), 325-333. Anichukwueze, C. C., Osuji, V. C., & Oguntegbe, E. E. (2020). Designing ethics and compliance training frameworks to drive measurable cultural and behavioral change. Int J Multidiscip Res Growth Eval, 1(3), 205-20. Anichukwueze, C. C., Osuji, V. C., & Oguntegbe, E. E. (2021a). Blockchain-based architectures for tamper-proof regulatory recordkeeping and real-time audit readiness. Int J Multidiscip Res Growth Eval, 2(6), 485-504. Anichukwueze, C. C., Osuji, V. C., & Oguntegbe, E. E. (2021b). Digital Marketing Compliance Risk Mitigation: Balancing Growth Objectives with Multi-Jurisdictional Regulations. Anichukwueze, C. C., Osuji, V. C., & Oguntegbe, E. E. (2022). LegalTech-Enabled Internal Audit Automation: Advancing Efficiency, Transparency, and Regulatory Preparedness. Anioke, S. C., & Atima, M. E. (2018). Regulatory Analytics Approaches for Improving Occupational Health Safety Outcomes Across Public and Private Workplaces. Anioke, S. C., & Atima, M. E. (2019). Digital Employer Risk Rating Frameworks Supporting Public Health Oriented Social Insurance Compliance Systems. Antonakakis, M., April, T., Bailey, M., Bernhard, M., Bursztein, E., Cochran, J. et al. (2017). Understanding the Mirai botnet. USENIX Security 2017, 1093 to 1110. Anwar, S. and Soltesz, B. (2016). Securing the smart grid. International Journal of Advanced Research in Computer Science, 7(1). Apruzzese, G., Colajanni, M., Ferretti, L., Guido, A. and Marchetti, M. (2018). On the effectiveness of machine and deep learning for cyber security. CyCon 2018, 371 to 390. Apruzzese, G., Colajanni, M., Ferretti, L. and Marchetti, M. (2019). Addressing adversarial attacks against security systems based on machine learning. International Conference on Cyber
More Articles from WORLD JOURNAL OF INNOVATION AND MODERN TECHNOLOGY
AI-Assisted Risk and Incident Analysis: Advances and Future Opportunities
Author: Uchechi Mary-Linda Unamma, Ifeanyichukwu Jeffrey Okwesa, Serif Oyindamola, Oyesiji, Abubakar Umar Abdulmalik
Influence of Artificial Intelligence Tools on Teachers’ Instructional Delivery in Public Senior Secondary Schools in Gokana and Khana Local Government Areas of Rivers State, Nigeria
Author: BIIBALOO Juliet Legborsi, EDO Barineka Lucky, PhD NWILE Charles Befii, PhD.
Community-Centered Digital Skills: Empowering Adults for Life- Long-Learning in Yola North Local Government Area
Author: Adamu Abdullahi Potiskum, Emeka Godwin Timothy, Lawan Ladan
Dielectric Performance of Natural Ester Insulating Fluids as a Sustainable Alternative to Mineral Transformer Oil: A Systematic Review
Author: Ude Kingsley Okechukwu, Ugwu Kelvin Ikechukwu, Mmamel Ngozi Juliana, Nnamani, Micheal Obiora
Artificial Intelligence and Inclusive Practices in Special Needs Education: Opportunities, Challenges, and Future Directions
Author: Rahima Ahmadu Ribadu, Bobboi Abubakar