Advances in Intrusion Detection Systems: Integrating Machine Learning, Deep Learning, IoT, and Federated Learning
Ziadul Amin Chowdhury, Muhammad Mahbubur Rahman, Tanvir Azhar · International Journal of Computer Applications · 2024
The integration of Machine Learning (ML) and Deep Learning (DL) techniques has ushered in a new era of Intrusion Detection Systems (IDS).These advanced approaches significantly enhance detection accuracy, enabling the identification of novel cyber threats and processing massive datasets to ensure robust and reliable network security.The synergy between IoT devices and Federated Learning empowers IDSs to handle distributed data sources and secure edge environments effectively.By leveraging diverse datasets, including network traffic, system logs, and user behavior, IDSs can construct comprehensive threat models and improve their overall effectiveness.This paper investigates cutting-edge methodologies and models based on ML, DL, IoT, and Federated Learning.The challenges associated with deploying DL and ML in IDS have been discussed, and potential avenues for future research have been proposed.This survey aims to guide researchers in adopting contemporary network security and intrusion detection techniques.