Machine Learning Approaches for Anomaly Detection in Network Security: Challenges, Methods and Advances

• Published in: 2024 9th International Conference on Communication and Electronics Systems (ICCES) pp. 2027 - 2031
• Main Authors: Rekha, D S B N S, Raju Gottumukkala, V.S.S.P., Vijaya Durga, Poodi Venkata, Upendra, Kolapalli Jistnasai, Eda, Shalini, Dianakamal, Gudapati
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.12.2024
• Subjects: 6G mobile communication; Adaptation models; Anomaly detection; Biological system modeling; Computer crime; Convolution Neural Networks; Deep learning; Internet of Things; Long Short-Term Memory; Machine Learning; Network security; Neural networks; Software-defined networks
• DOI: 10.1109/ICCES63552.2024.10859675

Nowadays cyberattacks are become a very serious problem in Networking, online transactions, and everywhere. So the complexity of network infrastructures has given serious difficulties for network security in recent years. To reduce cyberattacks Machine Learning(ML) has provided a reliable solution for network anomaly detection in various settings by including software-defined networks (SDNs), automobile networks, and the Internet of Things (IoT). This paper provides an overview of various machine learning (ML) methods for anomaly detection using supervised, unsupervised, and deep learning models. Long Short-Term Memory (LSTM) networks and Convolution Neural Networks (CNNs) are the best Deep Learning (DL) models for detecting complex and before undiscovered threats. In order to improve detection accuracy and computing efficiency, this work investigates the degree to which these techniques are applied in a number of contexts, including smart metering systems, vehicular ad hoc networks (VANETs), and Internet of Things network security.