Machine Learning Algorithms to Detect Deepfakes Fine Tuned for Anomaly Detection of IoT

Abstract

The internet of things (IoT) is a worldwide network of interconnected gadgets that enables devices to communicate with one another and share data in a continuous manner. Any deviation from the typical course of events is referred to as an anomaly, and it might serve as an early indicator that there is a problem. The authors differentiate themselves from previous tactics by requiring less time to identify and respond to attacks since they implement a variety of machine learning algorithms while the programme is running. This effort intends to establish a system for anomaly detection that is capable of screening IoT flaws and alerting the organization's CEO as well as the help network. The authors make use of a machine learning approach called k-nearest neighbor (KNN) in conjunction with a random forest (RF) algorithm in order to fine-tune the parameters of the spreading network. As a result, this framework improves the performance of the model without causing it to overfit.