Masters Thesis Defense “Deep Learning Approach for Intrusion Detection System(IDS) in an Internet of Things(IoT) network using Gated Recurrent Neural Networks (LSTM and GRU)” By Manoj Kumar Putchala

Committee:  Drs. Michelle Cheatham, Advisor, Adam Bryant, Michael Raymer, and Mateen Rizki

ABSTRACT:

The Internet of Things (IoT) is a complex paradigm where billions of devices are connected over a network. These connected devices form an intelligent system of systems that share the data without human-to-computer or human-to-human interaction. These systems extract meaningful data that can transform human lives, businesses and the world in significant ways. However, the reality of IoT is prone to countless cyber-attacks in the extremely hostile environment like internet. The recent hack of 2014 Jeep Cherokee, iStan pacemaker and German steel plant are few notable security breaches.

To secure an IoT system, the traditional high-end security solutions are not suitable, as IoT devices are of low storage capacity and less processing power. Moreover, the IoT devices are connected for longer time periods without human intervention. This raises a need to develop smart security solutions which are light-weighted, distributed and have high longevity of service. Rather than per-device security for numerous IoT devices, it is more feasible to implement security solutions for network data. The artificial intelligence theories like Machine Learning and Deep Learning have already proven their significance when dealt with heterogeneous data of various sizes. To substantiate this, in this research, we have applied concepts of Deep Learning and Transmission Control Protocol/Internet Protocol (TCP/IP) to build a light-weight distributed security solution with high durability for IoT network security.

First, we examined the ways of improving IoT architecture and proposed a light-weighted and multi-layered design for an IoT network. Second, we analyzed the existing applications of Machine Learning and Deep Learning to the IoT and the Cyber-Security. Third, we evaluated the deep learning’s Gated Recurrent Neural Networks (LSTM and GRU) on DARPA/KDD Cup ’99 intrusion detection dataset for each layer in the designed architecture. Finally, from the evaluated metrics, we proposed the best neural network design suitable for the IoT Intrusion Detection System. With an accuracy of 98.91% and False Alarm Rate of 0.76 %, this unique research outperformed the performance results of existing methods over KDD Cup ’99 data-set. For this first time in the IoT research, the concepts of Gated Recurrent Neural Networks are applied for the IoT security.