Batool Mastoi* and Gul Bano
Department of software Engineering, Mehran University of Engineering and Technology, Jamshoro, Sindh, Pakistan
*Corresponding Author: Batool Mastoi, Department of software Engineering, Mehran University of Engineering and Technology, Jamshoro, Sindh, Pakistan
Received: December 20, 2022; Published: December 27, 2022
DDOS attacks have become a widespread problem on the internet these days. The DDOS attack is a spiteful effort to dislocate the usual traffic of a targeted server, service, or network by crushing the target or its nearby infrastructure with a flood of Internet traffic. Artificial intelligence and Machine learning proved to be efficient in evaluating the performance of the system by using algorithms. The detection of DDOS attacks is a basic problem in machine learning. Due to the advancement of technology i.e. Cloud computing, it is a significantly difficult task to identify DDOS attacks because of computational complexities. This Study proposes a ML framework for detecting, Monitoring and providing prevention techniques for DDOS attacks and compares the performance of four frequently used algorithms (Nave Bayes, Decision Tree, Random Forest, and SVM). The dataset was validated by performing a T-test. OWASP ZAP and Weka Tool have been used for the analysis. 1031 samples were collected. The study found interesting remarks.
Keywords: DDOs Attack; Ml Algorithms; Owsap Zap; Risk
Citation: Batool Mastoi and Gul Bano. “Framework for Monitoring and Detection of DDOS Attacks using ML Algorithms".Acta Scientific Computer Sciences 5.1 (2023): 144-149.
Copyright: © 2023 Batool Mastoi and Gul Bano. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.