DDoS Attack Detection and Classification using Machine Learning Models with Real-Time Dataset Created
Harrsheetha Sasikumar
Harrsheeta Sasikumar*, Computer Science and Engineering, Panimalar Engineering College, Chennai, India.
Manuscript received on January 08, 2021. | Revised Manuscript received on January 15, 2021. | Manuscript published on January 30, 2021. | PP: 145-153 | Volume-9 Issue-5, January 2021. | Retrieval Number: 100.1/ijrte.E5217019521 | DOI: 10.35940/ijrte.E5217.019521
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Distributed Denial of Service (DDoS) attack is one of the common attack that is predominant in the cyber world. DDoS attack poses a serious threat to the internet users and affects the availability of services to legitimate users. DDOS attack is characterized by the blocking a particular service by paralyzing the victim’s resources so that they cannot be used to legitimate purpose leading to server breakdown. DDoS uses networked devices into remotely controlled bots and generates attack. The proposed system detects the DDoS attack and malware with high detection accuracy using machine learning algorithms. The real time traffic is generated using virtual instances running in a private cloud. The DDoS attack is detected by considering the various SNMP parameters and classifying using machine learning technique like bagging, boosting and ensemble models. Also, the various types of malware on the networked devices are prevent from being used as a bot for DDOS attack generation.
Keywords: Attacks, Intrusion Detection, Malware Detection, Machine Learning Models.