Multi-Layered AI-Driven Paradigm Shift in IoT Ecosystem Security

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 16 | 01 | Page :
    By

    Kazi Kutubuddin Sayyad Liyakat,

  • Heena T Shaikh,

  1. Professor, Department of Electronics and Telecommunication Engineering, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India
  2. Asst. Professor, Department of Electronics and Telecommunication Engineering, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India

Abstract

As the Internet of Things (IoT) continues to weave itself into the fabric of modern life—from smart homes and industrial automation to healthcare and urban infrastructure—the associated security vulnerabilities have become increasingly apparent. Traditional security mechanisms, often built on static rules and perimeter-based defenses, struggle to keep pace with the scale, heterogeneity, and dynamic nature of IoT ecosystems. In response, Artificial Intelligence (AI) has emerged as a transformative force in fortifying IoT environments against evolving cyber threats. The exponential expansion of the Internet of Things (IoT) has created an unprecedentedly complex and porous attack surface. Traditional, perimeter-based security paradigms are fundamentally inadequate for this decentralized, heterogeneous ecosystem. This paper proposes a novel framework: the Cognitive-Autonomic Security Mesh (CASM). CASM is a multi-layered, AI-native security architecture designed to provide proactive, adaptive, and resilient defense across the entire IoT stack—from the constrained endpoint to the cloud and back. It leverages a synergistic interplay of distributed artificial intelligence models to achieve a state of continuous self-learning, self-healing, and autonomous threat mitigation. By continuously learning from device interactions, network traffic patterns, and environmental inputs, the proposed method transcends rule-based limitations, enabling proactive defense mechanisms that evolve alongside emerging attack vectors. Deployed across edge, fog, and cloud layers, this AI-integrated approach enhances scalability, reduces false positives, and strengthens end-to-end security across distributed IoT networks.

Keywords: Artificial Intelligence, IoT, Security, Multi-layered AI, CASH, Accuracy, Precision, F1 score, Recall, Throughput

How to cite this article:
Kazi Kutubuddin Sayyad Liyakat, Heena T Shaikh. Multi-Layered AI-Driven Paradigm Shift in IoT Ecosystem Security. Journal of Communication Engineering & Systems. 2026; 16(01):-.
How to cite this URL:
Kazi Kutubuddin Sayyad Liyakat, Heena T Shaikh. Multi-Layered AI-Driven Paradigm Shift in IoT Ecosystem Security. Journal of Communication Engineering & Systems. 2026; 16(01):-. Available from: https://journals.stmjournals.com/joces/article=2026/view=242006


References

  1. Liyakat KK, Halli UM. Nanotechnology in IoT security. Journal of Nanoscience, Nanoengineering & Applications. 2022;12(3):11-6.
  2. Devanand WA, Raghunath RD, Baliram AS, Kazi K. Smart agriculture system using IoT. Int. J. Innov. Res. Technol. 2019 Mar;5(10).
  3. Hotkar PR, Kulkarni V, Kamble P, Kazi KS. Implementation of Low Power and area efficient carry select Adder. International Journal of Research in Engineering, Science and Management. 2019;2(4):183-4.
  4. Khatun MA, Chowdhury N, Uddin MN. Malicious nodes detection based on artificial neural network in iot environments. In2019 22nd International Conference on Computer and Information Technology (ICCIT) 2019 Dec 18 (pp. 1-6). IEEE.
  5. Nikita K, Supriya J. Design of Vehicle system using CAN Protocol. International Journal of Research in Applied science and Engineering Technology. 2020;8:1978- 83.
  6. Kundaliya BL, Hadia SK. Routing algorithms for wireless sensor networks: Analysed and compared. Wireless Personal Communications. 2020 Jan;110(1):85-107.
  7. Akansha K. Email security. Journal of Image Processing and Intelligent remote sensing. 2022 Oct;2(6):295-320.
  8. Sanchez-Reillo R, Gonzalez-Marcos A. Access control system with hand geometry verification and smart cards. IEEE Aerospace and Electronic Systems Magazine. 2000 Feb 29;15(2):45-8.
  9. Liu L, Yang J, Meng W. Detecting malicious nodes via gradient descent and support vector machine in Internet of Things. Computers & Electrical Engineering. 2019 Jul 1;77:339-53.
  10. Son M, Kim H. Blockchain-based secure firmware management system in IoT environment. In2019 21st International Conference on Advanced Communication Technology (ICACT) 2019 Feb 17 (pp. 142-146). IEEE.
  11. Jain N, Maitri. Big data and predictive analytics: a facilitator for talent management. InData Science Landscape: Towards Research Standards and Protocols 2018 Mar 2 (pp. 199-204). Singapore: Springer Singapore.
  12. Lee B, Lee JH. Blockchain-based secure firmware update for embedded devices in an Internet of Things environment. The Journal of supercomputing. 2017 Mar;73(3):1152-67.
  13. Golder A, Gupta D, Roy S, Al Ahasan MA, Haque MA. GSM Based Home Security Alarm System Using Arduino Using Mobile Call. In2023 IEEE 14th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) 2023 Oct 12 (pp. 0268-0274). IEEE.
  14. Al-Mashhadi HM, Alabiech MH. A survey of email service; attacks, security methods and protocols. International Journal of Computer Applications. 2017;162(11).
  15. Altmann J. Military uses of nanotechnology: perspectives and concerns. Security Dialogue. 2004 Mar;35(1):61-79.
Ahead of Print Subscription Review Article
Volume 16
01
Received 16/01/2026
Accepted 19/01/2026
Published 14/04/2026
Publication Time 88 Days
33

Login


My IP

PlumX Metrics