• Dr. K Vanitha
• Akash Balasubramani
• Akanksha
• Gautham N T
• Jayasurya P Gowda

The future of networking is in software defined networks, which allow for centralized network control by separating network devices' data and control plane. SDN can deliver superior administration and security of a network and enables us to program the network for improved speed and usability. DDOS attacks are the most severe and threatening attacks in a network. They can flood the network, block access to the server network with enormous packets, and exploit network resources to prevent answers for future incoming requests. Nonetheless, SDN is subject to attacks. DDOS attacks are known to only become more common in a cloud setting. To effectively detect and mitigate DDOS assaults in SDN, a method for doing so is described that combines statistics and machine learning techniques. The machine learning technique used in implementing this method has achieved an accuracy of 99.26% and a detection rate of 100% in detecting and mitigating DDOS assaults in a software defined network utilizing the Ryu controller and Mininet network simulator with OpenFlow SDN protocol.

An adaptive approach to Detect and Mitigate DDOS attack using machine learning

"An adaptive approach to Detect and Mitigate DDOS attack using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.o213-o218, May-2023, Available :http://www.jetir.org/papers/JETIR2305F25.pdf

"An adaptive approach to Detect and Mitigate DDOS attack using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppo213-o218, May-2023, Available at : http://www.jetir.org/papers/JETIR2305F25.pdf