Anomaly Network Traffic Detection of Wireless Network System
Dugganapalli Deepika, Deepika Pogiri, Lokesh Raj Pandravisham, Yashwanth Kumar Prudvi, Sathvik Reddy Ramannagari · 2024
Network traffic anomaly detection is a current topic in network security. Based on unsupervised learning, this paper constructs a Model for Detecting Irregularities in Network Data to solve the problems of high dimensions of abnormal traffic. Among the prevalent threats to network security, anomalies stand out as a significant menace, capable of causing system mal-functions and impeding proper network functionality. Detecting these anomalies is imperative for ensuring the uninterrupted operation of networks. While DL and ML algorithms have showcased their potential in detecting network anomalies, their efficacy remains relatively uncertain. This research study performs a detailed analysis of the algorithms (Isolation Forest and Local Outlier Factor) using the datasets to assess the ability to identify the network anomalies. This study proposes a thorough analysis of various applications of deep learning and machine learning, with the goal of enhancing network security.