Denial of Service Malevolent Traffic Identification and Prevention in Software Defined Networking
J. Ramprasath, A. B. Arockia Christopher, M. Balakrishnan, A. S. Muthanantha Murugavel · 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) · 2022
Nowadays, building secure networks is a challenge that challenges the computing industry growth. Because of the rise of the internet, the threat of a distributed denial of service attack has also grew. This can be prevented by an Intrusion Detection Systems (IDS), which detects malicious threats and unintended network access. The detailed analysis of the research study is compared to the current dataset in order to detect irregular network assaults. Classification techniques in Machine Learning (ML) are used to identify many types of threats. ML strategies may result in increased detection rates, a reduction in false positive rates, and low computing and communication costs. KDD cup99 is included in this article to examine ML algorithms performances for implementing the IDS. An experiment on IDS that makes use of ML algorithms such as Naive Bayes and k-means clustering for detecting the malicious flood.