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.
BT - 1st International Symposia on Computer and Information Sciences, ISCIS 2018 CY - London, United Kingdom DA - 07/2018 DO - 10.1007/978-3-319-95189-8_8 LA - eng N2 -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.
PB - Springer PP - London, United Kingdom PY - 2018 SN - 978-331995188-1 T2 - 1st International Symposia on Computer and Information Sciences, ISCIS 2018 TI - Deep learning with dense random neural networks for detecting attacks against IoT-connected home environments ER -