Modelling Deep Learning and Machine Learning Methods in IOT based Cybersecurity
Gurpreet Singh Chhabra, Rakesh Thoppaen Suresh Babu, K. Babu, Pravin B Khatkale, Onkar Ghige, P. William
Abstract
In this research, the incorporation of Deep Learning (DL) and Machine Learning (ML) into cybersecurity processes is investigated in great depth. The study also highlights the significant role that these technologies play in recognizing and minimizing cyber hazards. It is necessary to use contemporary security solutions since traditional security measures have not been able to keep up with the rapid expansion of cyberattacks. The ability of deep learning and machine learning algorithms to analyze patterns in big datasets makes it feasible to do real-time threat detection and predictive analytics. This makes it possible for organizations to increase their security postures. Within the scope of this study, several deep learning and machine learning models are evaluated using performance metrics such as accuracy, precision, recall, and F1-score across a wide range of cyber threat scenarios. The purpose of this evaluation is to establish the degree to which these models are effective. The findings illustrate how effectively these models adapt to a variety of cyber settings and how they contribute to the development of highly effective and adaptable cybersecurity defenses.