Research Article
An Adaptive Ensembled Neural Network-Based Approach to IoT Device Identification
@INPROCEEDINGS{10.1007/978-3-031-24386-8_12, author={Jingrun Ma and Yafei Sang and Yongzheng Zhang and Xiaolin Xu and Beibei Feng and Yuwei Zeng}, title={An Adaptive Ensembled Neural Network-Based Approach to IoT Device Identification}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 18th EAI International Conference, CollaborateCom 2022, Hangzhou, China, October 15-16, 2022, Proceedings, Part II}, proceedings_a={COLLABORATECOM PART 2}, year={2023}, month={1}, keywords={IoT Identification Traffic classification}, doi={10.1007/978-3-031-24386-8_12} }- Jingrun Ma
Yafei Sang
Yongzheng Zhang
Xiaolin Xu
Beibei Feng
Yuwei Zeng
Year: 2023
An Adaptive Ensembled Neural Network-Based Approach to IoT Device Identification
COLLABORATECOM PART 2
Springer
DOI: 10.1007/978-3-031-24386-8_12
Abstract
The Internet of Things (IoT) has developed rapidly in recent years and has been widely used in our daily life. An online report claimed that the connected IoT devices will reach the scale of 14.4 billion globally at the end of 2022. With the rapid and large-scale deployment of such devices, however, some severe security problems and challenges arised as well, especially in the field of IoT device management. Device identification is a prerequisite procedure to mitigate the above issues. Therefore, accurately identifying the deployed IoT devices plays a vital role in network management and cyber security. In this work, we come up with a spatio-temporal-based method that characterizes IoT device behaviors by leveraging the packet sequence features of IoT traffic, which is able to automatically extract the high-level features from raw IoT traffic. The further evaluation indicates that our method is capable of identifying diverse IoT devices with satisfactory accuracy.
