Research Article
Discretization-Based Ensemble Model for Robust Learning in IoT
@INPROCEEDINGS{10.1007/978-3-031-63992-0_23, author={Anahita Namvar and Chandra Thapa and Salil S. Kanhere}, title={Discretization-Based Ensemble Model for Robust Learning in IoT}, proceedings={Mobile and Ubiquitous Systems: Computing, Networking and Services. 20th EAI International Conference, MobiQuitous 2023, Melbourne, VIC, Australia, November 14--17, 2023, Proceedings, Part II}, proceedings_a={MOBIQUITOUS PART 2}, year={2024}, month={7}, keywords={Adversarial Robustness IoT Discretization Ensemble}, doi={10.1007/978-3-031-63992-0_23} }- Anahita Namvar
Chandra Thapa
Salil S. Kanhere
Year: 2024
Discretization-Based Ensemble Model for Robust Learning in IoT
MOBIQUITOUS PART 2
Springer
DOI: 10.1007/978-3-031-63992-0_23
Abstract
The rapid proliferation of Internet of Things (IoT) devices has introduced new challenges in network management and security. While machine learning models hold promise for identifying these devices, they remain vulnerable to adversarial attacks, undermining their accuracy and reliability. This paper addresses the need for robust IoT device identification by proposing a novel approach: a discretization-based ensemble stacking technique. This method harnesses both the protective properties of discretization and the generalization benefits of ensemble methods. Through extensive experimentation, we demonstrate the efficacy of our approach against various adversarial attacks, showcasing its potential to enhance the resilience and accuracy of IoT device identification models in dynamic and uncertain environments.
