Implementation of Cyber Threat Intelligence Platform on Internet of Things (IoT) using TinyML Approach for Deceiving Cyber Invasion

In recent past years' application of Internet of Things (IoT) technology has been radically enhanced in various domain across the sphere. Due to less computational capabilities and nonapplicability of conventional security protocol, both wired or wireless communication channel of IoT devices are facing major security issues and challenges in cyber security landscape. Enforcement of upgraded Tactics, Technology and Procedure (TTPs) by the modern cyber criminals turns the traditional signature based threat detection mechanism inefficient for implementation of resilient as well as comprehensive security measures in IoT artifacts. In this backdrop, integration of Cyber Threat Intelligence (CTI) platform and machine learning approach [1], with the conventional security mechanism assists us to develop an effective, robust and secure framework for the smart devices to combat all current and futuristic security concerns and develop an automated, responsive security architecture pertaining to the IoT devices. This paper focuses on the various security issues and challenges along with layer wise security protocols applicable for the IoT devices. Furthermore, author designed a TinyML based framework using Tensorflow module, amalgamated with CTI platform for predicting potential threat propagated to the smart devices employing Naïve Bayes supervised ML classifier and the final solution is predicting threat accurately 96.8% and 96.3% for training and test dataset respectively.