ANOMALY DETECTION IN NETWORK TRAFFIC: EVALUATION MACHINE LEARNING CLASSIFIERS

Abstract

The rapid proliferation of Internet of Things (IoT) devices has necessitated the development of efficient and reliable anomaly detection mechanisms to ensure system integrity, security, and performance. Traditional centralized anomaly detection systems are increasingly inadequate due to their scalability issues, latency, and inability to handle the diverse and voluminous data generated by IoT edge devices. This project proposes an innovative Machine Learning (ML)-driven anomaly detection framework specifically designed for IoT edge devices, leveraging the Alternating Direction Method of Multipliers (ADMM) for effective frequency management. Therefore, this proposed framework addresses the critical challenges of limited computational resources, real-time processing requirements, and device heterogeneity by distributing the computational load and enabling local anomaly detection at the edge. By integrating advanced ML techniques with ADMM-based optimization, the system ensures accurate and timely detection of anomalies, thereby enhancing the reliability and security of IoT networks. Additionally, this approach optimizes the performance and energy efficiency of edge devices, facilitating scalable and robust anomaly detection across diverse IoT environments. The significance of this project lies in its potential to revolutionize IoT edge management by providing a scalable, efficient, and reliable anomaly detection solution. Enhanced reliability ensures continuous and consistent operation, while improved security protects against potential breaches. Optimized performance and resource efficiency further empower edge devices to handle the increasing demands of modern IoT applications. This project not only addresses current limitations but also fosters innovation in IoT management, positioning itself at the forefront of advancements in edge computing and ML-driven anomaly detection