Deep learning with dense random neural networks for detecting attacks against IoT-connected home environments

TytułDeep learning with dense random neural networks for detecting attacks against IoT-connected home environments
Publication TypeConference Paper
Rok publikacji2018
AutorzyBrun O, Yin Y, Gelenbe E, Y. Kadioglu M, Augusto-Gonzalez J, Ramos M
Conference Name1st International Symposia on Computer and Information Sciences, ISCIS 2018
Date Published07/2018
PublisherSpringer
Conference LocationLondon, United Kingdom
ISBN Number978-331995188-1
Abstract

In this paper, we analyze the network attacks that can be launched against IoT gateways, identify the relevant metrics to detect them, and explain how they can be computed from packet captures. We also present the principles and design of a deep learning-based approach using dense random neural networks (RNN) for the online detection of network attacks. Empirical validation results on packet captures in which attacks were inserted show that the Dense RNN correctly detects attacks.

DOI10.1007/978-3-319-95189-8_8

Historia zmian

Data aktualizacji: 30/08/2018 - 09:40; autor zmian: Monika Adler (madler@iitis.pl)