Improvised Ensemble Model for Fast Prediction of DoS/DDoS Attacks in Various Networks

This study investigates the application of machine learning techniques for detecting and mitigating the growing threat of DoS/DDoS attacks in online activities. With the increasing reliance on technology, ensuring the security of computer networks is of utmost importance. Our focus is on effective detection of DDoS attacks, where the victim's computer is overwhelmed by traffic from multiple sources. We propose the use of ensemble methods and leverage two datasets, namely the MyHomeNetwork Traffic Dataset and the NSL-KDD dataset, to evaluate the detection accuracy. By employing various machine learning classification algorithms, our system accurately identifies DDoS attacks with an impressive 99% accuracy rate. These findings underscore the efficacy of our approach in safeguarding computer networks against DDoS threats.