MACHINE LEARNING FOR REAL-TIME CYBER THREAT DETECTION: A COMPARATIVE STUDY

Due to the potential of machine learning to detect cyber threats, it has become an important component of the security industry's efforts to identify and prevent attacks. However, choosing the right approach to implement this technology can be challenging due to the wide variety of models and methods available. This review paper aims to identify the most effective techniques for analyzing and detecting cyber threats. The paper begins by providing an introduction to the subject and discusses the importance of detecting cyber threats. It then explores the research objectives and problem statement. The research questions are then addressed. The review section of this paper provides an overview of the various types of cyber threats and their evolution. It also explores the limitations of current techniques in the fight against these threats. The section on the selection criteria and search strategy describes the steps involved in finding relevant literature. It also covers the evaluation parameters and metrics that are used in comparative analysis. The discussion section of the paper provides a summary of the literature and a comparison of the various techniques. It also explores their weaknesses and strengths. This leads to the development of a framework that will allow organizations to use machine learning to detect cyber threats. The paper's concluding section contains a summary of the findings, conclusions, and future directions of future research. The review evaluates machine learning's capabilities for real-time detection of cyber threats, and it proposes a framework to address certain limitations and gaps in current approaches