TY - GEN
T1 - Multi-Level IoT Device Identification
AU - Jiao, Ruohong
AU - Liu, Zhe
AU - Liu, Liang
AU - Ge, Chunpeng
AU - Hancke, Gerhard
N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).
PY - 2021/12
Y1 - 2021/12
N2 - The rapid development of the Internet of Things (IoT) has brought challenges to IoT platforms for high-efficiency deployments and low-budget management. Identifying IoT devices is the prerequisite for monitoring, protecting, and managing them. Considering different providers and IoT device renovation, centralized device identification solutions require large amounts of training data and frequent model updates. Traditional solutions based on machine learning cannot preserve identification precision for the long term at a low cost in reality. In this paper, we propose a multi-level IoT device identification framework, alleviating the problem of novel class detection and large-scale updating of IoT models in IoT device identification. The proposed framework improves the usability of device identification technology in the real world. We also designed an IoT device identification method, achieving an average identification accuracy of 93.37 %. With this proposed multi-level IoT device identification framework, IoT device identification can achieve a high precision over a long time.
AB - The rapid development of the Internet of Things (IoT) has brought challenges to IoT platforms for high-efficiency deployments and low-budget management. Identifying IoT devices is the prerequisite for monitoring, protecting, and managing them. Considering different providers and IoT device renovation, centralized device identification solutions require large amounts of training data and frequent model updates. Traditional solutions based on machine learning cannot preserve identification precision for the long term at a low cost in reality. In this paper, we propose a multi-level IoT device identification framework, alleviating the problem of novel class detection and large-scale updating of IoT models in IoT device identification. The proposed framework improves the usability of device identification technology in the real world. We also designed an IoT device identification method, achieving an average identification accuracy of 93.37 %. With this proposed multi-level IoT device identification framework, IoT device identification can achieve a high precision over a long time.
KW - Device Fingerprinting
KW - Devices Identification
KW - IoT Security
UR - http://www.scopus.com/inward/record.url?scp=85129869452&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85129869452&origin=recordpage
U2 - 10.1109/ICPADS53394.2021.00073
DO - 10.1109/ICPADS53394.2021.00073
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 978-1-6654-0879-0
T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS
SP - 538
EP - 547
BT - Proceedings - 2021 IEEE 27th International Conference on Parallel and Distributed Systems
PB - IEEE
T2 - 27th IEEE International Conference on Parallel and Distributed Systems (ICPADS 2021)
Y2 - 14 December 2021 through 16 December 2021
ER -