Imperial College London
Portrait Picture

Dr Anna Maria Mandalari

Faculty of Engineering, Institute for Security Science & Technology

Honorary Research Fellow
 
 
 
//

Contact

 

anna-maria.mandalari Website

 
 
//

Location

 

ObservatorySouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Kolcun:2020,
author = {Kolcun, R and Popescu, DA and Safronov, V and Yadav, P and Mandalari, AM and Xie, Y and Mortier, R and Haddadi, H},
publisher = {arXiv},
title = {The case for retraining of ML models for IoT device identification at  the edge},
url = {http://arxiv.org/abs/2011.08605v1},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
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, usingresources available at the edge of the network.  In this paper, we compare the accuracy of five different machine learningmodels (tree-based and neural network-based) for identifying IoT devices byusing packet trace data from a large IoT test-bed, showing that all models needto be updated over time to avoid significant degradation in accuracy. In orderto effectively update the models, we find that it is necessary to use datagathered from the deployment environment, e.g., the household. We thereforeevaluate our approach using hardware resources and data sources representativeof those that would be available at the edge of the network, such as in an IoTdeployment. We show that updating neural network-based models at the edge isfeasible, as they require low computational and memory resources and theirstructure is amenable to being updated. Our results show that it is possible toachieve device identification and categorization with over 80% and 90% accuracyrespectively at the edge.
AU  - Kolcun,R
AU  - Popescu,DA
AU  - Safronov,V
AU  - Yadav,P
AU  - Mandalari,AM
AU  - Xie,Y
AU  - Mortier,R
AU  - Haddadi,H
PB  - arXiv
PY  - 2020///
TI  - The case for retraining of ML models for IoT device identification at  the edge
UR  - http://arxiv.org/abs/2011.08605v1
UR  - http://hdl.handle.net/10044/1/84617
ER  -
Download