A Comprehensive Survey on Recent Advancements in Machine Learningfor Cybersecurity Threat Detection and Prevention

Abstract

Cybersecurity threats have escalated in complexity and frequency, necessitating robust and intelligent detection and prevention mechanisms. Machine learning (ML) has emerged as a pivotal technology in addressing these threats by providing adaptive and scalable solutions. This paper presents a comprehensive survey of the latest advancements in machine learning for cybersecurity threat detection and prevention, with a focus on studies conducted up to 2024. We review state-of-the-art methodologies, highlight existing challenges, and discuss future research directions. Our findings indicate that deep learning, federated learning, and adversarial ML are at the forefront of cybersecurity research, offering promising solutions against evolving threats.