Intelligent Network Traffic Prediction Using Graph Neural Networks

Abstract

The Widespread Deployment Of Wireless Communication Technology Has Made The Wi-Fi Network More Susceptible To Sophisticated Cyber-attacks, Which Include De-authentication Attacks, Rogue Access Points, Traffic Flooding, And Protocol Misuse. The Limitation Of The Traditional Intrusion Detection System In Detecting Unknown Attacks In Real-time Has Led To The Development Of This Paper, Which Presents An Intelligent Real-time Detection System For Wi-Fi Network Attacks Using Machine Learning And Graph Neural Networks (GNNs) Technology. The Proposed System Monitors The Wi-Fi Network Traffic In Real-time And Extracts Essential Features From The IEEE 802.11 Protocol Frames, Which Include Packet Rates, Signal Strength, Protocol Behaviour, And Time-based Features. The Proposed System Uses The Extracted Features To Classify The Network Behaviour As Normal Or Abnormal Using The Trained Machine Learning Models. The Proposed System Effectively Uses The GNN Technology To Detect The Complex Relationships Between The Network Entities, Which Makes It More Efficient In Detecting Network Intrusions. The Proposed System Has Been Tested And Found Effective In Terms Of Accuracy, Reducing False Positives, And Ensuring Real-time Detection Of Network Intrusions, Which Makes It More Suitable For Modern Enterprise And Public Network Environments.

Keywords