Analysis of DDoS Attacks and Development of Software Solutions Using Machine Learning for Detection and Mitigation

This research paper aims to study DDoS (Distributed Denial of Service) attacks, which are among the most critical security threats in the digital age. The causes of these attacks, their adverse impacts on online services, and programmatic and technical methods for detecting and mitigating them are discussed. A software model was developed to simulate a DDoS attack using tools such as Python and Scapy, alongside proposing practical solutions to address these attacks. The performance of three machine learning algorithms (Naïve Bayes, ANN, and CNN) in detecting DDoS attacks was evaluated based on accuracy, true positive rate (TPR), and false positive rate (FPR) criteria. Finally, recommendations are provided to enhance cybersecurity and reduce the risks posed by such attacks.