DDoS Detection using Machine Learning

Abstract

In the cybersecurity domain, Denial of Service (DoS) attacks maliciously disrupt the availability of systems, inundating them with packets or requests. Distributed Denial of Service (DDoS) attacks compound this challenge, utilizing multiple compromised sources. Recognizing and classifying these attacks swiftly is critical for safeguarding online platforms. Our research focuses on DDoS attacks, leveraging Machine Learning (ML) to distinguish between normal and malicious network behavior. Anchored by the apaDDoS-dataset, our approach aims to empower systems to autonomously identify and respond to threats, enhancing digital security.