P2P Traffic Intelligence System Employing Wavelet Bandwidth Analytics for Multivariate Anomaly Reasoning

Abstract

Modern digital infrastructures including enterprise networks, cloud computing platforms, IoT ecosystems, and online service environments continuously generate vast volumes of real-time data such as network packets, authentication logs, and system performance metrics. This rapid data generation necessitates efficient, intelligent, and real-time security monitoring mechanisms. To address these challenges, this work proposes an automated and scalable AI-driven security framework for real-time anomaly detection and authentication threat analysis. Initially, machine learning models such as K-Nearest Neighbor (KNN) and Support Vector Classifier (SVC) are utilized to learn network behavior patterns and distinguish between normal and malicious activities. Although effective, these models exhibit limitations including high computational complexity, sensitivity to feature scaling, and inefficiency in handling large-scale or probabilistic data scenarios. To overcome these constraints, a Naive Bayes Classifier (NBC) is adopted as the primary probabilistic inference model within the framework. By leveraging Bayesian decision theory and modeling conditional feature dependencies, NBC enables efficient estimation of threat probabilities with reduced computational overhead and improved scalability for high-dimensional datasets. The proposed system incorporates data preprocessing, class balancing techniques, multi-model training, and deployment through a web-based Flask interface to facilitate real-time threat detection. Performance evaluation is conducted using standard metrics such as accuracy, precision, recall, and F1-score, demonstrating reliable anomaly detection and classification capabilities. The results validate that the proposed framework provides a robust, scalable, and efficient solution for enhancing real-time security intelligence in modern digital environments.