Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection

arXiv:2404.04188v1 Announce Type: new
Abstract: The growing cybersecurity threats make it essential to use high-quality data to train Machine Learning (ML) models for network traffic analysis, without noisy or missing data. By selecting the most relevant features for cyber-attack detection, it is possible to improve both the robustness and computational efficiency of the models used in a cybersecurity system. This work presents a feature selection and consensus process that combines multiple methods and applies them to several network datasets. Two …

analysis arxiv attack computational cs.cr cs.lg cs.ni cyber cyber-attack cybersecurity cybersecurity threats data detection efficiency feature features high machine machine learning missing network network traffic network traffic analysis noisy quality relevant robustness threats traffic traffic analysis train