| Téléchargement | - Voir la version finale : Mitigating adversarial attacks against IoT profiling (PDF, 2.9 Mio)
|
|---|
| DOI | Trouver le DOI : https://doi.org/10.3390/electronics13132646 |
|---|
| Auteur | Rechercher : Neto, Euclides Carlos PintoIdentifiant ORCID : https://orcid.org/0000-0002-1241-6391; Rechercher : Dadkhah, SajjadIdentifiant ORCID : https://orcid.org/0000-0002-5582-0255; Rechercher : Sadeghi, SomayehIdentifiant ORCID : https://orcid.org/0000-0003-2264-5662; Rechercher : Molyneaux, Heather1Identifiant ORCID : https://orcid.org/0000-0003-0673-7815 |
|---|
| Affiliation | - Conseil national de recherches Canada. Technologies numériques
|
|---|
| Format | Texte, Article |
|---|
| Sujet | internet of things (IoT); security; IoT profiling; deep learning (DL); adversarial attacks; data poisoning; label flipping |
|---|
| Résumé | Internet of Things (IoT) applications have been helping society in several ways. However, challenges still must be faced to enable efficient and secure IoT operations. In this context, IoT profiling refers to the service of identifying and classifying IoT devices’ behavior based on different features using different approaches (e.g., Deep Learning). Data poisoning and adversarial attacks are challenging to detect and mitigate and can degrade the performance of a trained model. Thereupon, the main goal of this research is to propose the Overlapping Label Recovery (OLR) framework to mitigate the effects of label-flipping attacks in Deep-Learning-based IoT profiling. OLR uses Random Forests (RF) as underlying cleaners to recover labels. After that, the dataset is re-evaluated and new labels are produced to minimize the impact of label flipping. OLR can be configured using different hyperparameters and we investigate how different values can improve the recovery procedure. The results obtained by evaluating Deep Learning (DL) models using a poisoned version of the CIC IoT Dataset 2022 demonstrate that training overlap needs to be controlled to maintain good performance and that the proposed strategy improves the overall profiling performance in all cases investigated. |
|---|
| Date de publication | 2024-07-05 |
|---|
| Maison d’édition | MDPI |
|---|
| Licence | |
|---|
| Dans | |
|---|
| Langue | anglais |
|---|
| Publications évaluées par des pairs | Oui |
|---|
| Exporter la notice | Exporter en format RIS |
|---|
| Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
|---|
| Identificateur de l’enregistrement | 7a2b219a-09cf-4c9e-9529-aea761b12ca5 |
|---|
| Enregistrement créé | 2024-10-22 |
|---|
| Enregistrement modifié | 2024-10-24 |
|---|
