Abstract
Many strategies use ML algorithms for intelligent IDS as part of the development of IoT security. These algorithms are quite susceptible to being manipulated to provide biased results. A variety of contradictory threats are constantly present throughout the use of ML, such as the erroneous poisoning of learning data sets or the alteration of model parameters. So, in this post, we’ve suggested a blockchain-based approach to using intelligent contracts to secure the decision-making process of the learning model. We will dissect decision-making functions based on the categorization of SVM and MLP on the chain for a more comprehensive Blockchain integration.
Disclosure statement
No potential conflict of interest was reported by the authors.