IDS based Trust Computation Algorithm in Industrial IoT using Machine Learning Techniques

Vaibhav Prakash Repe; Sarika Jadhav

IDS based Trust Computation Algorithm in Industrial IoT using Machine Learning Techniques

Author(s)	Mr. Vaibhav Prakash Repe, Dr. Sarika Jadhav
Country	India
Abstract	The rapid evolution of Industrial Internet of Things (IIoT) systems has added tremendous improvements to automation, process observables, and smart decision making in fields like medicine, manufacturing and smart infrastructure. With this increased automation, the IIoT systems become more vulnerable. Specially, maintaining trust and shielding IIoT systems from new, advanced, and growing cyber-attacks has proven to be a challenge. Typical Intrusion Detection Systems (IDS) detect intrusions to a network from attacks, but are insufficient to new advanced threats and attacks. Furthermore, such IDS fail to assess trust and dynamically adjust to a more sophisticated level in real time. This study outlines the details of such a challenge, and addresses these challenges with a hybrid trust-based intrusion detection framework that combines machine learning for efficient computation of trust in IIoT adaption environments. The model proposed in this study provides an assessment of validity of nodes in the network from an IIoT adaption framework, and such assessment is based on and integrated from several dimensions of control including communication, collaboration, and level of control exercised. Adaptive machine learning and control is based on a combination of both unsupervised and supervised control. More specifically, the supervision of control employs support vector machines (SVM), Naive Bayes (NB), and hybrid machine learning (HML) model based on random forest with AdaBoost. The evaluation methodology included both simulated datasets and datasets from real-world IoT applications. The results showed that Naïve Bayes scored 96.13% in accuracy, 96.4% in precision, 96.13% in recall, and 96.26% in F1 score; and SVM scored 93.2% in accuracy, 96.52% in precision, and 94.81% in F1 score. The results indicated that the proposed model, the HML, achieved a competing 98.2% in accuracy, 96.43% in precision, 98.2% in recall, and 97.31% in the F1 score, thus outperforming all other models in testing and demonstrating superior performance, robustness, and adaptability. In summary, combining the trust-based evaluation model and hybrid machine learning approaches provides a significant improvement in the detection and protection of IIoT systems; thus, it becomes applicable for real-time deployment in mission-critical systems.
Keywords	IIoT, Intrusion Detection System, Machine Learning, Trust Management, Support Vector Machine, Naïve Bayes
Field	Engineering
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-12

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

IDS based Trust Computation Algorithm in Industrial IoT using Machine Learning Techniques

Share this