A project that is used to analyse multiple machine learning classifers for DDoS detection from botnets and finalize the best classifer.
Abstract:
An increasing number of Internet of Things (IoT) devices are connecting to the Internet, yet many of these devices are fundamentally insecure, exposing the Internet to a variety of attacks. Botnets such as Mirai have used insecure consumer IoT devices to conduct distributed denial of service (DDoS) attacks on critical Internet infrastructure. This motivates the development of new techniques to automatically detect consumer IoT attack traffic. In this paper, we study DDos attack by botnet infected Iot devices using multiple machine learning classifiers. DDoS detection in IoT network traffic with a variety of machine learning classifiers, including neural networks. These results indicate that home gateway routers or other network middleboxes could detect local IoT device sources of DDoS attacks using low-cost machine learning algorithms and traffic data that is flow-based and protocol-agnostic. We will be classifying all the data and provide graph for each and find the best algorithm that has the highest accuracy for detection of attack.
classification with feature reduction test.
Datasets: https://drive.google.com/drive/folders/14vkF8LeoXpQVqY_sJs0YJmxYo66Zj0sh?usp=sharing
Work done with Google Colab.