International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 09 Issue: 05 | May 2022
p-ISSN: 2395-0072
www.irjet.net
Literature Review on DDOS Attacks Detection Using SVM algorithm. Manasvi Suryavanshi 1, Nikita Pawar2, Sanathkumar Pillai3 1,2,3 Student
and Department of Computer Engineering, ISB&M School of Technology, SPPU, India. ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Software-defined network (SDN) is a network architecture that is used to build, and design the hardware components
virtually. In the traditional network, it's not possible to change dynamically, because it's a fixed connection. SDN is a good way but still is weak to DDoS attacks. The DDoS attack is a problem for the internet. To avert the DDoS attack, the machine learning algorithm can be used. The DDoS attack is the multiple collaborated systems that are used to target a particular server at the same time. In SDN The Data plane takes care of the network traffic based on the decision made by the controller. The Control plane chooses the course of traffic by computing the routing tables. We have used a machine learning technique namely Support Vector Machine (SVM) to detect malicious traffic using two datasets namely KDD99 and CIS-CIC-IDS 2018. Our test outcome shows that the Support Vector Machine (SVM) algorithm provides better accuracy and detection rate. Key Words: Machine learning, DDoS, SVM, SDN, KDD99, CIS-CIC-IDS
1. INTRODUCTION Software-Defined Networking is an emerging paradigm that overcomes the limitations of conventional network architecture by separating the control from data plane devices. SDN consists of planes such as the data plane, control plane, and application plane. The Data plane takes care of the network traffic based on the decision made by the controller. The Control plane chooses the course of traffic by computing the routing tables. SDN architecture boosts the network performance by breaking up the network control and forward function. The control programs managing a logically centralized controller will control multiple routers across the network.
1.1 Machine Learning Machine Learning is a subfield of Artificial Intelligence, that teaches computers to do what comes naturally to humans and animals: learn from experience. It has various types: Supervised learning, which trains a model on known input and output data and predicts future outputs. Unsupervised Learning, which finds hidden patterns in input data. Reinforcement Learning is a reinforcement learning agent that can perceive and interpret its environment, take actions and learn through trial and error.
1.2 Supervised Learning A supervised learning algorithm takes a known set of input data to the data(output) and trains a model to generate predictions for the response to new data. It comprises two techniques classification and regression to develop machine learning models. Classification models identify input data. The data can then be filtered into specific groups. SVM: In Machine Learning one of the most important tasks is when you have a bunch of objects that you want to classify, for that you are required to use SVM. Support Vector Machines (SVM) are some of the simplest and arguably the most elegant methods for classification. Each object you want to classify is represented as a point in an n-dimensional space and the coordinates of this point are usually called features. SVMs perform the classification test by drawing a hyperplane that is a line in 2D or a plane in 3D in such a way that all points of one class are on one side of the hyperplane and all points of the other class are on the other side and while there could be multiple such hyperplanes SVM tries to find the one that best separates the two classes.
© 2022, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 3335