At its peak, the Internet-of-Things will largely be composed of low-power devices with wireless radios attached. Yet, secure authentication of these devices amidst adversaries with much higher power and computational capability remains a challenge, even for advanced cryptographic and wireless security protocols. For instance, a high-power software radio could simply replay chunks of signals from a low-power device to emulate it. This paper presents a deep-learning classifier that learns hardware imperfections of low-power radios that are challenging to emulate, even for high- power adversaries. We build an LSTM framework, specifically sensitive to signal imperfections that persist over long durations. Experimental results from a testbed of 30 low-power nodes demonstrate high resilience to advanced software radio adversaries.
Description
A Deep Learning Approach to IoT Authentication | IEEE Conference Publication | IEEE Xplore
%0 Conference Paper
%1 8422832
%A Das, Rajshekhar
%A Gadre, Akshay
%A Zhang, Shanghang
%A Kumar, Swarun
%A Moura, Jose M. F.
%B 2018 IEEE International Conference on Communications (ICC)
%D 2018
%K authentication iot
%P 1-6
%R 10.1109/ICC.2018.8422832
%T A Deep Learning Approach to IoT Authentication
%U https://ieeexplore.ieee.org/abstract/document/8422832
%X At its peak, the Internet-of-Things will largely be composed of low-power devices with wireless radios attached. Yet, secure authentication of these devices amidst adversaries with much higher power and computational capability remains a challenge, even for advanced cryptographic and wireless security protocols. For instance, a high-power software radio could simply replay chunks of signals from a low-power device to emulate it. This paper presents a deep-learning classifier that learns hardware imperfections of low-power radios that are challenging to emulate, even for high- power adversaries. We build an LSTM framework, specifically sensitive to signal imperfections that persist over long durations. Experimental results from a testbed of 30 low-power nodes demonstrate high resilience to advanced software radio adversaries.
@inproceedings{8422832,
abstract = {At its peak, the Internet-of-Things will largely be composed of low-power devices with wireless radios attached. Yet, secure authentication of these devices amidst adversaries with much higher power and computational capability remains a challenge, even for advanced cryptographic and wireless security protocols. For instance, a high-power software radio could simply replay chunks of signals from a low-power device to emulate it. This paper presents a deep-learning classifier that learns hardware imperfections of low-power radios that are challenging to emulate, even for high- power adversaries. We build an LSTM framework, specifically sensitive to signal imperfections that persist over long durations. Experimental results from a testbed of 30 low-power nodes demonstrate high resilience to advanced software radio adversaries.},
added-at = {2022-08-15T02:17:38.000+0200},
author = {Das, Rajshekhar and Gadre, Akshay and Zhang, Shanghang and Kumar, Swarun and Moura, Jose M. F.},
biburl = {https://www.bibsonomy.org/bibtex/2071f19360fdd6d9ad094570a50f7dc23/danilofukuoka},
booktitle = {2018 IEEE International Conference on Communications (ICC)},
description = {A Deep Learning Approach to IoT Authentication | IEEE Conference Publication | IEEE Xplore},
doi = {10.1109/ICC.2018.8422832},
interhash = {ec8593ca14a14686baf3eab1582e52b4},
intrahash = {071f19360fdd6d9ad094570a50f7dc23},
issn = {1938-1883},
keywords = {authentication iot},
month = may,
pages = {1-6},
timestamp = {2022-08-15T02:17:38.000+0200},
title = {A Deep Learning Approach to IoT Authentication},
url = {https://ieeexplore.ieee.org/abstract/document/8422832},
year = 2018
}