Machine Learning Algorithms for DoS and DDoS Cyberattacks Detection in Real-Time Environment

Amid the escalating global threat of severe cyberattacks, integrating Machine Learning (ML) into cybersecurity has become a critical research priority. This study addresses this imperative by training several distinct ML models using a refined dataset that underwent a meticulous double-feature reduction process. The objective is to enable the accurate detection of different malicious network traffic, mainly DoS and DDoS, within real-time operational environments. To validate the efficacy of ML algorithms in controlled settings, network packets are captured and analyzed in real-time using a synergistic combination of PyShark and CICFlowMeter tools. The results of this investigation are highly promising, revealing the successful development of robust intrusion detection models through a novel dual-feature selection approach. Notably, these models achieved exceptional accuracy rates in detecting cyberattacks, demonstrating a remarkable 99% success.