The Challenges in SDN/ML Based Network Security : A Survey

TL;DR

This survey reviews the intersection of machine learning and SDN security, highlighting vulnerabilities, attack methods, and emphasizing the need for more secure development practices in ML-based SDN security models.

Contribution

It uniquely combines analysis of ML vulnerabilities with SDN security challenges, providing a comprehensive overview of recent applications and attack methods.

Findings

ML-based SDN security models are vulnerable to specific attacks

Existing surveys do not cover both ML vulnerabilities and SDN security together

The paper advocates for more secure development processes in ML/SDN security applications

Abstract

Machine Learning is gaining popularity in the network security domain as many more network-enabled devices get connected, as malicious activities become stealthier, and as new technologies like Software Defined Networking (SDN) emerge. Sitting at the application layer and communicating with the control layer, machine learning based SDN security models exercise a huge influence on the routing/switching of the entire SDN. Compromising the models is consequently a very desirable goal. Previous surveys have been done on either adversarial machine learning or the general vulnerabilities of SDNs but not both. Through examination of the latest ML-based SDN security applications and a good look at ML/SDN specific vulnerabilities accompanied by common attack methods on ML, this paper serves as a unique survey, making a case for more secure development processes of ML-based SDN security applications.