This study uses modern machine learning approaches to detect distributed denial of service (DDoS) assaults in a novel way. DDoS attacks are a danger to cybersecurity because they attempt to stop a targeted network, service, or server from operating normally by flooding it with Internet traffic. Our approach reliably detects and mitigates these harmful behaviors by utilizing real-time data analysis along with supervised learning techniques. For training and validating our model, we used an extensive dataset that included normal and attack traffic patterns. When compared to conventional approaches, the results show a considerable reduction in false positives as well as negatives and a high detection accuracy.