Employing Supervised Learning Techniques for DDoS Attack Detection
Atul Kumar, Ishu Sharma · 2023
Distributed Denial of Service attack is widely utilized by cyber attackers to target organizations to gain financial advantages. The different organizations aim to tackle these attacks, but manual work or precautions will not ful fill the requirements of the system. Machine learning techniques can boost the security system by automatically detecting these cyberattacks. In this research paper, supervisedlearning techniques are utilized to detect DDoS attacks in network infrastructure. DDoS attack detection using machine learning (ML) involves training machine learning algorithms to recognize patterns and anomalies in network traffic that may indicate a DDoS attack. The NSL-KDD dataset maintained by the Canadian Institute of Cybersecurity is utilized to accomplish the designated task. The results show that algorithm K neighbors classifier and Random forest classifier are capable of classifying the normal and with attack traffic log. On the other hand, the random forest classifier shows very low accuracy for the same dataset.