TrustSys: Trusted Decision Making Scheme for Collaborative Artificial Intelligence of Things

Many IoT-based applications have inherited the artificial intelligence of things (AIoT) techniques to explore new services and benefits of smart recording and monitoring generated information. However, hundreds of hacking incidents caused by highly sophisticated attackers have generated serious risk...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2023-01, Vol.19 (1), p.1059-1068
Main Authors: Rathee, Geetanjali, Garg, Sahil, Kaddoum, Georges, Choi, Bong Jun, Hassan, Mohammad Mehedi, AlQahtani, Salman A.
Format: Article
Language:English
Subjects:
Accuracy
Agent-based models
Artificial intelligence
Back propagation
Backpropagation
Bayes methods
Bayesian’s classification
Collaboration
Communication
Decision making
Decision trees
decision-making scheme
Internet of Things
Monitoring
Reagents
Real-time systems
secure AIoT
Security
trusted collaborative AIoT
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many IoT-based applications have inherited the artificial intelligence of things (AIoT) techniques to explore new services and benefits of smart recording and monitoring generated information. However, hundreds of hacking incidents caused by highly sophisticated attackers have generated serious risks, where they compromised various IoT sensors for their benefits, impeding the growth of AIoT. Various security schemes have been proposed in the literature; however, it is critical to determine the legitimacy of AIoT devices in real-time scenarios during the initial deployment of the network. Therefore, this article aims to provide a secure, reliable, and trusted decision-making scheme using multiattribute methods in collaborative AIoT. The proposed system uses backpropagation and Bayesian's rule to ensure a fast and accurate decision. In addition, agent-based modeling and population-based modeling trust schemes are used to compute the legitimacy of the communicating model. Further, the proposed system is validated over various security measures against the various decision-based conventional methods such as Fuzzy c-means, REPTree, and random tree in terms of time, accuracy, replay attack, data falsification attack, recall, region of convergence, and F-Measure. The proposed mechanism achieves 93% improvement over accuracy and attack identification against existing mechanisms.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2022.3173006