Artificial Intelligence Assisted IoT Data Intrusion Detection
Kumar A. Shukla, Shahanawaj Ahamad, G.Nageswara Rao, Avein Jabar Al-Asadi, Ankur Gupta, Makhan Kumbhkar
Abstract
It has become increasingly important since the introduction of Internet of Things (IoT) technology to ensure the security of IoT networks. Network anomalies and threats can be identified and predicted using a variety of intrusion detection systems (IDS). Despite the fact that the Internet of Things is vulnerable to attacks, early detection of malicious behavior can prevent data from being compromised. In this work, the primary goal is to develop machine artificial intelligence energy efficient models that can be used to detect attacks on the Internet of Things network. Normal and attack data from the IoT environment must be collected in order to construct a model. The Bayesian Network, the Artificial Neural Network, and the Support Vector Machine are considered to have the most promise. Using roundtrip time and power consumption data, a traditional three-layer Artificial Neural Network is put through its paces in the real world.