Internet of Thing Device
Internet of Things (IoT) devices are increasingly reliant on efficient and secure machine learning (ML) for tasks ranging from anomaly detection and intrusion prevention to resource optimization and personalized services. Current research emphasizes developing lightweight ML models, often employing neural networks (like CNNs and MLPs) and ensemble methods (e.g., XGBoost), optimized for resource-constrained IoT hardware and tailored to address privacy concerns through techniques such as federated learning and differential privacy. This work is crucial for enabling the secure and sustainable deployment of increasingly sophisticated IoT applications across diverse sectors, improving both security and energy efficiency.
Papers
TFormer: A Transmission-Friendly ViT Model for IoT Devices
Zhichao Lu, Chuntao Ding, Felix Juefei-Xu, Vishnu Naresh Boddeti, Shangguang Wang, Yun Yang
ARGUS: Context-Based Detection of Stealthy IoT Infiltration Attacks
Phillip Rieger, Marco Chilese, Reham Mohamed, Markus Miettinen, Hossein Fereidooni, Ahmad-Reza Sadeghi