Cybersecurity of AI and IoT Integrated for Mechanical Industries

Year : 2025 | Volume : 12 | Issue : 02 | Page : 27 33
    By

    Siddesh B,

  1. Research Scholar, Department of Studies in Mechanical Engineering, University BDT College of Engineering, Karnataka, India

Abstract

By facilitating the concept of Industry 4.0, the intersection of artificial intelligence (AI) and the Internet of Things (IoT) has changed the mechanical industries. When combined, these technologies are advancing process optimization, predictive maintenance, real-time condition monitoring, and smarter automation. In order to give proactive system control and intelligent decision-making, AI algorithms mine large datasets generated via IoT devices for relevant patterns. In the meanwhile, IoT guarantees smooth communication between machine parts, which permits dynamic system reconfiguration and remote diagnostics. These skills lead to considerable cost savings, improved productivity, and enhanced product quality. However, this integration also introduces substantial cybersecurity vulnerabilities. Threats such as data poisoning, adversarial attacks, botnets, malware, and distributed denial-of-service (DDoS) pose critical risks. Such attacks can compromise sensor data integrity, disrupt automated decision-making processes, and cause severe production downtime or physical damage. These risks are exacerbated by the prevalence of legacy systems in mechanical industries, which often lack modern security features and sufficient computational resources to implement complex defenses. This study presents a structured cybersecurity framework tailored for AI-IoT ecosystems in mechanical applications. Using the STRIDE threat modeling technique, attack vectors are identified, and a multi-layered security architecture is proposed. Key components include secure device authentication with Public Key Infrastructure (PKI), TLS 1.3 encrypted communications, adversarially trained AI models, AI-driven anomaly detection systems, and edge-based secure computing. A detailed case study involving a CNC lathe integrated with IoT sensors and AI models validates the framework’s effectiveness. Compliance with international cybersecurity standards such as IEC 62443, ISO/IEC 27001, and the NIST Cybersecurity Framework is evaluated to ensure industrial applicability. The results demonstrate enhanced anomaly detection accuracy (96.2%), improved system resilience, and reduced attack impact. Future enhancements incorporating blockchain-based audit trails, federated learning for secure AI model training, and zero-trust security architectures are discussed. This comprehensive cybersecurity approach is essential to protect intelligent, connected, and autonomous mechanical systems against evolving cyber threats.

Keywords: Cybersecurity, artificial intelligence, internet of things, mechanical industry, industrial automation, predictive maintenance, smart manufacturing

[This article belongs to Journal of Mechatronics and Automation ]

How to cite this article:
Siddesh B. Cybersecurity of AI and IoT Integrated for Mechanical Industries. Journal of Mechatronics and Automation. 2025; 12(02):27-33.
How to cite this URL:
Siddesh B. Cybersecurity of AI and IoT Integrated for Mechanical Industries. Journal of Mechatronics and Automation. 2025; 12(02):27-33. Available from: https://journals.stmjournals.com/joma/article=2025/view=222367


References

  1. Kott A, Wang C, Erbacher R Cybersecurity of Smart Manufacturing Systems. IEEE Trans Syst Man Cybern. 2021; 51(1): 1–13.
  2. AlSalem TS, Almaiah MA, Lutfi A. Cybersecurity risk analysis in the IoT: A systematic review. Electronics. 2023;12(18):3958. doi:10.3390/electronics12183958.
  3. NIST. Cybersecurity Framework for Critical Infrastructure. Gaithersburg, MD: NIST;
  4. Yang Y, et al. A Survey on Security and Privacy Issues in Internet-of-Things. IEEE IoT J. 2017; 4(5): 1250–1258.
  5. Liu J, Zhang Cyber-Physical Security for Smart Manufacturing Systems: A Survey. IEEE Access. 2021; 9: 123456–123470.
  6. Mitchell R, Chen I-R. A Survey of Intrusion Detection Techniques for Cyber-Physical Systems. ACM Comput 2014; 46(4): 55.1–55.29.
  7. IEC 62443. Industrial Communication Networks-Network and System Security. International Electrotechnical Commission; 2018.
  8. ISO/IEC 27001. Information Security Management. International Organization for Standardization;
  9. Wollschlaeger M, Sauter T, Jasperneite The future of industrial communication: Automation networks in the era of the Internet of Things and Industry 4.0. IEEE Ind Electron Mag. 2017 Mar; 11(1): 17–27.
  10. Rahman A, Hossain M, Almurib Federated Learning for Privacy Preservation in IoT-based Industrial Monitoring. Sensors. 2022; 22(7): 2567–2579.
  11. HardwareBee. (2021 Jun 22). The Ultimate Guide to IoT Architecture. [Online]. Hardware Bee. Available: https://hardwarebee.com/iot-architecture/.
  12. Luxcontrol and POST Luxembourg. (2023 Nov 20). Un ‘Cyberscore’ pour s’assurer de la sécurité des données. [Online]. Smart Cities Mag. Available: https://smartcitiesmag.lu/web/un-cyberscore-pour-sassurer-de-la-securite-des-donnees/.
  13. Shahbazi Z, Byun YC. Smart manufacturing real-time analysis based on blockchain and machine learning approaches. Appl Sci. 2021;11(8):3535. doi:10.3390/app11083535.
  14. Ammar M, Russello G, Crispo Internet of Things: A survey on the security of IoT frameworks. J Inf Secur Appl. 2018; 38: 8–27.
  15. Papernot N, et al. The Limitations of Deep Learning in Adversarial Settings. In Proc IEEE Euro S&P. 2016; 372–387.
  16. Albahri S, et al. IoT-based Cybersecurity Risk Assessment in Industry 4.0: A Systematic Review. Future Gener Comput Syst. 2020; 113: 584–603.
Regular Issue Subscription Original Research
Volume 12
Issue 02
Received 15/05/2025
Accepted 06/07/2025
Published 16/07/2025
Publication Time 62 Days
157

Login


My IP

PlumX Metrics