Date of Publication :23rd March 2023

Abstract: In cyber security, machine learning is becoming increasingly significant. The main goal of implementing machine learning in cyber security is to improve malware detection over conventional methods, which rely on human interaction, by making it more actionable, scalable, and efficient. Machine learning problems in the cyber security field call for effective methodical and theoretical management. Deep learning, support vector machines, and Bayesian classification, among other machine learning and statistical techniques, have all shown promise in resisting cyber-attacks. To create intelligent security systems, it is essential to identify hidden trends and insights in network data and to build a corresponding data-driven machine-learning model to stop these attacks. It has been highlighted how machine learning techniques have been used to reduce cyber security dangers that are now present. It has also been discussed how these cutting-edge models have drawbacks and how types of attack patterns have changed over the past ten years. Our objective is to evaluate how well these machine learning methods defend against the growing hazard of malware that affects the world in our online community.

Reference :