Visible to the public Machine Learning for Network Resiliency and Consistency

TitleMachine Learning for Network Resiliency and Consistency
Publication TypeConference Paper
Year of Publication2019
AuthorsHussein, A., Salman, O., Chehab, A., Elhajj, I., Kayssi, A.
Conference Name2019 Sixth International Conference on Software Defined Systems (SDS)
Date Publishedjun
Keywordsadaptability, ARS, artificial intelligence, artificial intelligence resiliency system, Computer architecture, consistency test scenario, consistency verification system, convolutional neural nets, convolutional neural networks, data privacy, Deep Learning, deep learning architectures, feature extraction, flow tables, global overview, learning (artificial intelligence), machine learning, network configurations, network consistency, network resilience, network resiliency, programmable networking, pubcrawl, resilience, Resiliency, SDN, security, security system, software defined networking

Being able to describe a specific network as consistent is a large step towards resiliency. Next to the importance of security lies the necessity of consistency verification. Attackers are currently focusing on targeting small and crutial goals such as network configurations or flow tables. These types of attacks would defy the whole purpose of a security system when built on top of an inconsistent network. Advances in Artificial Intelligence (AI) are playing a key role in ensuring a fast responce to the large number of evolving threats. Software Defined Networking (SDN), being centralized by design, offers a global overview of the network. Robustness and adaptability are part of a package offered by programmable networking, which drove us to consider the integration between both AI and SDN. The general goal of our series is to achieve an Artificial Intelligence Resiliency System (ARS). The aim of this paper is to propose a new AI-based consistency verification system, which will be part of ARS in our future work. The comparison of different deep learning architectures shows that Convolutional Neural Networks (CNN) give the best results with an accuracy of 99.39% on our dataset and 96% on our consistency test scenario.

Citation Keyhussein_machine_2019