Detection of DDoS attacks using deep learning
Jeff Jiju Manathara, Kris Shibu, Satvik Shankar, Kamalesh Singaravelan, Gokul Kannan Sadasivam · 2024
Distributed Denial of Service (DDoS) attacks pose a significant threat to the availability and reliability of networked services. Traditional DDoS detection methods are often unable to keep up with the increasing sophistication of attackers, leading to the need for more advanced detection techniques. Deep Learning has emerged as a promising approach for detecting DDoS attacks due to its ability to learn complex patterns and features from data. This paper proposes a DDoS detection system using Deep Learning techniques. The system uses a deep learning model to analyze network traffic data and classify it as normal or malicious. The proposed system is evaluated on the CIC-DDoS2019 dataset and benign records from the CSE-CIC-IDS2018 and CIC-IDS2017 datasets. The detection system was trained and tested on all attacks covered in the CIC-DDoS2019 dataset. The model showed an accuracy of 0.9921, precision of 0.9943, recall of 0.9916, F1-score of 0.9929, Kappa score of 0.9840 and Area Under Curve score of 0.9918. Overall, the proposed DDoS detection system using Deep Learning provides a promising approach for detecting DDoS attacks and can be integrated into existing network security infrastructure to enhance the overall security posture of networked services.