Leveraging Artificial Intelligence to Secure Wireless Network: Exploring Threats, Existing Approaches, and Proposed Mitigation Strategies

The exponential growth of network has introduced new Internet-of-Things (IoT) use cases that has enabling us convenience and comfort. The surge of IoT devices due to the capabilities brought by fifth generation (5G) have given rise to security threats and attacks, particularly malware attacks IoT botnets have been an alarming issue, where smart devices can be manipulated by malicious actors to commence subsequent attacks such as Denial of Service (DoS). Traditional and complex security techniques may not be a viable solution towards these resource-constrained devices with limited processing power. Machine Learning techniques (ML) are the rising trend, and it is often used in Intrusion Detection Systems and Network Anomaly Detection. This paper emphasizes on analyzing and comparing various ML models on the IoT-23 dataset. It aims to predict anomalies and conclude the model with optimal performance and least computational time cost that can be used for network anomaly detection systems with real-time data in future works. The ML models used in this paper are Decision Trees (DT), K-nearest neighbours (KNN), Random Forest (RF), Naïve Bayes (NB) and Histogram Gradient Boosting (HGB). DT displayed the best performance with an accuracy score of 73% and F1 score of 0.49 with a time cost of 28.22 seconds.

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.