Adversarial Evasion Attacks Practicality in Networks: Testing the Impact of Dynamic Learning

arXiv:2306.05494v2 Announce Type: replace-cross
Abstract: Machine Learning (ML) has become ubiquitous, and its deployment in Network Intrusion Detection Systems (NIDS) is inevitable due to its automated nature and high accuracy compared to traditional models in processing and classifying large volumes of data. However, ML has been found to have several flaws, most importantly, adversarial attacks, which aim to trick ML models into producing faulty predictions. While most adversarial attack research focuses on computer vision datasets, recent studies have explored the …

abstract accuracy adversarial arxiv attacks automated become cs.cr cs.lg cs.ni data deployment detection dynamic evasion found however impact machine machine learning nature network networks processing systems testing type