To provide useful insights to security aspects in Software Defined Networks (SDNs).


This is a collaborative work between:


With the advent of Software Defined Networks (SDNs), there has been a rapid advancement in the area of cloud computing. It is now scalable, cheaper, and easier to manage. However, SDNs are more prone to security vulnerabilities as compared to legacy systems. Therefore, machine-learning techniques are now deployed in the SDN infrastructure for the detection of malicious traffic.

In this research theme, we devise machine-learning frameworks for detecting malicious traffic, that can be subsequently deployed in an Intrusion Detection System (IDS). We use publicly available datasets, viz. NSL-KDD dataset to understand the non-linearity of the original feature space. This assists us in devising deep-learning based models to classify normal- and malicious- traffic data.

Using Andrews curve and t-Distributed Stochastic Neighbor Embedding (t-SNE) plot on the NSL-KDD dataset, we can visualize the non-linearity of the input feature space.


Please refer to the publications.