Anomaly Detection over SDN Using Machine Learning and Deep Learning for Securing Smart City

Abstract

The security over data is now a major concern for all applications. Attacks over data are going to be increasing day by day. Therefore, there is a need of security mechanism over all devices responsible for transfer of data over the network. An Intrusion Detection System (IDS) has been designed in order to detect different types of attacks over the system. IDS may be categorized Network Intrusion Detection System (NIDS) and Host Intrusion Detection System (HIDS). NIDS and HIDS are employed by the user depending on the requirement such as whether the user aims to find attacks over the whole network or just over a host. An IDS best works over Software Defined Networks (SDN) rather than traditional networks. Many of today’s applications reside over SDN. SDN is preferred over traditional because of its flexibility and agile property. This chapter mainly introduces various algorithms of intrusion detection like support vector machine (SVM), random forest (RF), K-means, Principal Component Analysis (PCA) and Self-Organizing Map (SOM), which are basically machine learning (ML) algorithms. ML algorithms may be supervised, unsupervised and semi-supervised learning algorithms. Besides ML algorithms, this chapter also introduces some deep learning algorithms used for intrusion detection. Examples are Recurrent Neural Network (RNN) and Deep Belief Network (DBN) etc.