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 for the online detection of network attacks. Empirical validation results on packet captures in which attacks were inserted show that the Deep Neural Network correctly detects attacks.
https://hal.laas.fr/hal-02062091 Contributor : Olivier BrunConnect in order to contact the contributor Submitted on : Friday, March 8, 2019 - 3:25:10 PM Last modification on : Monday, July 4, 2022 - 9:32:15 AM Long-term archiving on: : Monday, June 10, 2019 - 3:25:03 PM
Olivier Brun, yonghua yin, Javier Augusto-Gonzalez, Manuel Ramos, Erol Gelenbe. IoT Attack Detection with Deep Learning. ISCIS Security Workshop, Feb 2018, Londres, United Kingdom. ⟨hal-02062091⟩