Machine Learning-Based Intrusion Detection for Mitigating Denial of Service Attacks in Wireless Sensor Networks
K. Yasotha, K. Meenakshisundaram · 2023
Due to the characteristics of certain networks, particularly their constrained hardware capabilities, and infrastructure-less design, the widespread adoption of Wireless Sensor Networks (WSNs) has resulted in a number of security vulnerabilities. One of the most frequent threats to these networks is the denial-of-service attack. It is difficult to build an intrusion detection and prevention system to reduce the consequences of a denial-of-service attack. The use of a few machine learning techniques is suggested in this research as a way to identify vulnerabilities on a specified dataset. Regular profiles and various Denial of Service attack scenarios in WSNs are both included in the dataset that was used. According to the experimental findings, the hyperparameter tuning technique outperformed other techniques with greater true positive rates (higher) and better false positive rates (lower).