ISSN : 2663-2187

DoS Attack Detection using Machine Learning Techniques

Main Article Content

Sudhir Kumar Pandey, Shambhu Shankar Bharti, Zafar Ayub Ansari, Ajeet Kumar, Bhawana Singh, Moazzam Haidari
» doi: 10.48047/AFJBS.6.Si4.2024.3248-3263

Abstract

Numerous conventional articles have been written focusing on the topic of DoS/DDoS attacks. The majority of these present studies on DoS attacks from the attacker's perspective. Although these research works present assessments of vulnerabilities and then defenses of possible targets, they do not address the attack-enabling 'attack tools'. Despite this, DoS attacks have been extensively evaluated through other various types of security mechanisms which are pre-deployed to avoid DoS attacks. There is no descriptive overview or survey which mainly presents the present techniques, tools, and best practices to avoid DoS attacks. Therefore, this survey is both novel and informative to the researchers and readers in this field.A denial-of-service attack (DoS) is one of the most feared threats of the cyber world. DoS attack is easy to execute, but it is difficult to defend. In recent years, the impact of DoS attacks is widely addressed due to the rising number of DoS attacks. In this paper, we provide an extensive summary and analysis of the present techniques, tools, and best practices which are used to detect and defend against DoS attacks. We also applied Some Machine learning Algorithms with NSL KDD dataset in order to detect DoS attack. We have achieved best result with accuracy of 98.36 in Logistic Regression Algorithm.

Article Details