Paper Contents
Abstract
As the frequency and complexity of network attacks increase, traditional methods of intrusion detection, such as signature-based systems, struggle to keep up. Machine learning (ML) presents a promising approach for identifying network intrusions, including previously unseen (zero-day) attacks. This survey explores the application of machine learning in network attack detection, reviewing existing techniques, challenges, and opportunities. It provides an overview of commonly used datasets, methods, and evaluation metrics, followed by a discussion on the limitations and future directions for enhancing real-time attack detection.
Copyright
Copyright © 2024 Abitha S.. This is an open access article distributed under the Creative Commons Attribution License.
