Affiliation:
1. School of Cyber Science and Engineering, Southeast University, China
2. School of Computer Science and Engineering, Southeast University, China
Abstract
Radio frequency fingerprint identification (RFFI) is a promising technique for smartphone identification. However, we find that the temperature of the RF front end in smartphones can significantly impact the RF features, including the carrier frequency offset (CFO) and statistical RF features. The unstable RF features caused by temperature changes can negatively affect the performance of state-of-the-art RFFI approaches. To this end, we propose the RF-TESI solution for smartphone identification under temperature variation. First, we construct a dataset by extracting temperature and RF features. In the dataset, the extracted temperature values constitute a set of temperature values and each registered temperature value corresponds to a group of RF features. Next, we evaluate the distinctiveness of RF features across smartphones to select the most suitable RF fingerprint. Then, we train multiple random forest models, each tagged with a registered temperature. In addition, because there are still many temperatures out of the temperature set, we design an RF fingerprint estimation method to estimate RF fingerprints at unregistered temperatures. Finally, the experiments show RF-TESI demonstrates satisfactory performance under different scenarios, taking into account variations in temperature, time and position. Besides, our proposed approach is better than all state-of-the-art approaches in smartphone identification.
Funder
National Natural Science Foundation of China
Key R&D Program of Jiangsu Province
Jiangsu Provincial Key Laboratory of Network and Information Security
Key Laboratory of Computer Network and Information Integration of the Ministry of Education of China
Fundamental Research Funds for the Central Universities
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications