Network Traffic Analysis and Anomaly Detection in a Simulated Environment Using Explainable AI

This paper presents a novel approach for network traffic analysis and anomaly detection using interpretable models in a simulated environment.We leverage Mininet to create a virtual network, generate traffic, and capture data using Wireshark.Our approach employs decision tree models for traffic analysis and rule-based systems for anomaly detection, ensuring transparency and interpretability.The results demonstrate the effectiveness of interpretable models in providing actionable insights for network management and security.Our findings suggest that interpretable AI techniques can significantly enhance the trust and reliability of network analysis tools.