Threat Vector Segregation for Endpoint Security
The enormous evolution of web-based applications on the public Internet has accomplished universal communication among billions of Smart IoT (Internet of Things) devices and such smart devices communicate with each other through the network. Simultaneously, cyber-attackers have gained enough knowledge on attacking the Internet and information on Secured systems. Distributed Denial of Services evolved as a serious threat for organizations, these attacks must be mitigated immediately for preventing damages to the business. In Information and Cloud Security, DDoS attack is one of the main concerning successful attack procedures. Since DDoS attack can deny and disturb the service of one or more IoT nodes simultaneously, which causes the loss of data for any company. In other words, this will be a serious threat to the organization. ML models are implemented for resolving various Cybersecurity related problems such as Malware detections, spam mails, vulnerabilities in software, detection of an anomaly, biometric and facial recognition, and many other areas. It is essential to simulate the discrete event. DDoS attack model to evaluate the efficiency of the detection model for in-house study on DDoS attacks and preventions. This paper proposes a model to analyze the impact of DDoS (Distributed Denial of Service). The implemented model was developed using Mininet and POX controller on open source. The resultant network traffic is generated as the dataset. The values of the dataset were compared and plotted with various Machine learning methods for the prediction of DDoS attacks.
International Journal of Advance Research, Ideas and Innovations in Technology (IJARIIT- August 2021 Volume 7-Issue 4)