A COMPREHENSIVE REVIEW OF MACHINE LEARNING AND DEEP LEARNING APPLICATIONS IN CYBERSECURITY: AN INTERDISCIPLINARY APPROACH

Abstract

Cybersecurity is increasingly becoming a critical concern as the complexity and frequency of cyber-attacks continue to rise. Machine learning (ML) and deep learning (DL) have emerged as powerful tools to enhance cybersecurity systems, offering dynamic capabilities in real-time threat detection, anomaly detection, and intrusion prevention. This article (45) presents a systematic review of the applications of ML and DL in cybersecurity, adhering to the PRISMA guidelines. The review covers several key domains, including network security, cloud security, and Internet of Things (IoT) security, highlighting how ML/DL models like convolutional neural networks (CNNs) and recurrent neural networks (RNNs) outperform traditional rule-based systems. It also addresses challenges such as adversarial attacks, data privacy concerns, and the computational resource demands of DL models. Current solutions like adversarial training, federated learning, and model optimization techniques are examined for their potential to mitigate these issues. The findings suggest that while ML/DL technologies hold great promise, further research and innovation are necessary to overcome the inherent challenges, ensuring that these systems can be deployed effectively and securely in real-world environments.