Published Paper Details:

Distributed Denial-of-Service (DDoS) attacks have become a serious problem in cybersecurity. This can cause temporary or long-term loss of service to users. These attacks mainly target e-commerce platforms, online services, and financial institutions. Detecting DDoS attacks is essential because they cause serious problems. Detection of DDoS attacks can be effectively achieved using supervised machine learning techniques. This project presents an approach for detecting Distributed Denial of Service (DDoS) attacks using Support Vector Machine (SVM), a supervised machine learning algorithm. The methodology involves storing network traffic data in SQLite3 for efficient management and retrieval. The collected data undergoes preprocessing, including the handling of missing values and feature scaling with StandardScaler, to enhance the accuracy and robustness of the detection model. Experimental results highlight the effectiveness of SVM in distinguishing between normal and malicious traffic, thereby contributing to improved network security. In this paper, we propose new techniques for launching and mitigating DDoS attacks that clearly outperform existing techniques. We also classify DDoS attack techniques as well as the techniques used in their detection, and thus try to provide a broad scoping of the DDoS problem. We also compare our attack module with some of the available tools.