Wi-Fi Traffic Anomaly Detection Using Isolation Forest Algorithm

With the increasing use of wireless networks in daily life, ensuring network security has become very important. Wi-Fi networks are often affected by unusual activities such as unauthorized access or signal disturbances. In this paper, we propose a real-time Wi-Fi traffic anomaly detection system using the Isolation Forest algorithm. The system continuously monitors network behaviour by analysing parameters like packet size and transmission duration. Since the model is based on an unsupervised learning approach, it does not require labelled data. A simple dashboard is also developed to display the results in real time. The proposed system is efficient, easy to implement, and capable of detecting abnormal patterns effectively.