Publications

BibTex format

@inproceedings{Kolcun:2021,
author = {Kolcun, R and Popescu, DA and Safronov, V and Yadav, P and Mandalari, AM and Mortier, R and Haddadi, H},
pages = {1--9},
publisher = {IFIP},
title = {Revisiting IoT device identification},
url = {http://arxiv.org/abs/2107.07818v1},
year = {2021}
}

Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Internet-of-Things (IoT) devices are known to be the source of many securityproblems, and as such, they would greatly benefit from automated management.This requires robustly identifying devices so that appropriate network securitypolicies can be applied. We address this challenge by exploring how toaccurately identify IoT devices based on their network behavior, whileleveraging approaches previously proposed by other researchers.  We compare the accuracy of four different previously proposed machinelearning models (tree-based and neural network-based) for identifying IoTdevices. We use packet trace data collected over a period of six months from alarge IoT test-bed. We show that, while all models achieve high accuracy whenevaluated on the same dataset as they were trained on, their accuracy degradesover time, when evaluated on data collected outside the training set. We showthat on average the models' accuracy degrades after a couple of weeks by up to40 percentage points (on average between 12 and 21 percentage points). We arguethat, in order to keep the models' accuracy at a high level, these need to becontinuously updated.
AU  - Kolcun,R
AU  - Popescu,DA
AU  - Safronov,V
AU  - Yadav,P
AU  - Mandalari,AM
AU  - Mortier,R
AU  - Haddadi,H
EP  - 9
PB  - IFIP
PY  - 2021///
SP  - 1
TI  - Revisiting IoT device identification
UR  - http://arxiv.org/abs/2107.07818v1
UR  - https://dl.ifip.org/db/conf/tma/tma2021/index.html
UR  - http://hdl.handle.net/10044/1/91652
ER  -

Download

Dr Anna Maria Mandalari

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)