Visible to the public A Comparative Study of Off-Line Deep Learning Based Network Intrusion DetectionConflict Detection Enabled

TitleA Comparative Study of Off-Line Deep Learning Based Network Intrusion Detection
Publication TypeConference Paper
Year of Publication2018
AuthorsJiaqi Yan, Illinois Institute of Technology, Dong Jin, Illinois Institute of Technology, Cheol Won Lee, National Research Institute, South Korea, Ping Liu, Illinois Institute of Technology
Conference Name10th International Conference on Ubiquitous and Future Networks
Date Published07/2018
Conference LocationPrague, Czech Republic
KeywordsAutomated Synthesis Framework for Network Security and Resilience, Deep Learning, NetLearner, network intrusion detection systems, NIDS, UIUC

Abstract--Network intrusion detection systems (NIDS) are essential security building-blocks for today's organizations to ensure safe and trusted communication of information. In this paper, we study the feasibility of off-line deep learning based NIDSes by constructing the detection engine with multiple advanced deep learning models and conducting a quantitative and comparative evaluation of those models. We first introduce the general deep learning methodology and its potential implication on the network intrusion detection problem. We then review multiple machine learning solutions to two network intrusion detection tasks (NSL-KDD and UNSW-NB15 datasets). We develop a TensorFlow-based deep learning library, called NetLearner, and implement a handful of cutting-edge deep learning models for NIDS. Finally, we conduct a quantitative and comparative performance evaluation of those models using NetLearner.

Citation Keynode-56331

Other available formats:

A Comparative Study of Off-Line Deep Learning Based on Network Intrusion Detection