Abstract: In the modern world, internet has become a major part in everyone’s life. Most of businesses have now gone digital and internet is playing a major role in their success. Internet has enabled businesses to have larger market to which they can sell their products. One important component of the internet is the server. All the devices in the internet are broadly either a server or a client. Server stores the data that are then accessed by the clients. Distributed Denial-of-Service is a network attack on the servers. This attack targets the availability of the server by overwhelming them by a flood of internet traffic. This prevents the server from giving services to the legitimate users. DDoS attack causes significant losses to the organization. In this paper, we discuss a ensemble modelling based approach to mitigate this problem. Ensemble modelling is a process where multiple model which are different fundamentally are combined to make one classifier model.We try to predict the type of DDoS attack by developing a ensemble model by combining Naïve Bayes, Random Forest, Multilayer Perceptron, Stochastic Gradient Descent . The accuracy score of 98.62 percent has been achieved. It can be concluded that this system proves to be an effective deterrent for DDoS attacks.
Keywords: DDoS attack,http-flood, udp-flood, smurf , machine learning , ensemble model
|
DOI:
10.17148/IJARCCE.2022.11747
