Machine Learning Based Effective Classification of Distributed Denial of Service Attacks
Aanshi Bhardwaj1, Veenu Mangat2, Renu Vig3
1Aanshi Bhardwaj*, M.E., Department of Information Technology ,UIET, Panjab University, Chandigarh (Panjab), India.
2Veenu Mangat, M.E., Department of Information Technology ,UIET, Panjab University, Chandigarh (Panjab), India.
3Renu Vig, Ph.D, Department of Engineering and Technology, Panjab University, Chandigarh (Panjab), India.
Manuscript received on November 14, 2019. | Revised Manuscript received on 23 November, 2019. | Manuscript published on December 10, 2019. | PP: 1060-1064 | Volume-9 Issue-2, December 2019. | Retrieval Number: L29941081219/2019©BEIESP | DOI: 10.35940/ijitee.L2994.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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 Attack (DDoS) is a deadliest weapon which overwhelm the server or network by sending flood of packets towards it. The attack disrupts the services running on the target thereby blocking the legitimate traffic accessing its services. Various advanced machine learning techniques have been applied for detection of different types of DDoS attacks but still the attack remains a potential threat to the world. There are mainly two broad categories of machine learning techniques: supervised machine learning approach and unsupervised machine learning approach. Supervised machine learning approach requires labelled attack traffic datasets whereas unsupervised machine learning approach analyses incoming network traffic and then categorizes it. In this paper we have attempted to apply four different classifiers for the detection of DDoS attacks. The four classifiers applied are Logistic Regression, Naïve Bayes, K- Nearest Neighbor and Artificial Neural Network. The chosen classifiers provide stable results when there is a large dataset. We compared their detection accuracy on KDD dataset which is a benchmark dataset in the field of network security. This paper is novel as it explains each pre-processing step with python conversion functions and explained in detail all the classifiers and detection accuracy with their functions in python as well.
Keywords: Machine Learning, Logistic Regression, K-NN, Naïve Bayes, Artificial Neural Network.
Scope of the Article: Machine Learning