Abstract

The rapid proliferation of interconnected devices and the increasing complexity of digital networks in the modern era have resulted in a surge of diverse and voluminous network traffic. This growth poses considerable challenges in effectively distinguishing between normal and malicious data flows. As cyber threats continue to evolve, traditional traffic classification methods struggle to keep pace with the dynamic and multifaceted security challenges of contemporary networks. In this context, ensuring robust network security has become an imperative. This research aims to address these challenges by developing a machine learning-based approach to accurately classify and segregate malicious traffic from legitimate traffic, thereby strengthening overall network defence mechanisms.