A Novel Model-Based Security Scheme for LoRa Key Generation

Gao, Jiayao; Xu, Weitao; Kanhere, Salil S.; Jha, Sanjay; Kim, Jun Young; Huang, Walter; Hu, Wen

doi:10.1145/3412382.3458256

Cited by 13 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two main advantages of radio frequency fingerprinting are as follows: (i) it is theoretically secured and hard to imitate, (ii) it is suitable for devices with limited power and computing resources since it does not need extra transmission, but rather uses standard communication signals. Wireless identification is also widely used in localization scenarios [14][15][16][17][18][19][20]. There are two kinds of features that are commonly used as transceiver fingerprints.…”

Section: Radio Frequency Fingerprintingmentioning

confidence: 99%

Leveraging Deep Learning for IoT Transceiver Identification

Gao

Fan

Zhao³

et al. 2023

Entropy

View full text Add to dashboard Cite

With the increasing demand for Internet of Things (IoT) network applications, the lack of adequate identification and authentication has become a significant security concern. Radio frequency fingerprinting techniques, which utilize regular radio traffic as the identification source, were then proposed to provide a more secured identification approach compared to traditional security methods. Such solutions take hardware-level characteristics as device fingerprints to mitigate the risk of pre-shared key leakage and lower computational complexity. However, the existing studies suffer from problems such as location dependence. In this study, we have proposed a novel scheme for further exploiting the spectrogram and the carrier frequency offset (CFO) as identification sources. A convolutional neural network (CNN) is chosen as the classifier. The scheme addressed the location-dependence problem in the existing identification schemes. Experimental evaluations with data collected in the real world have indicated that the proposed approach can achieve 80% accuracy even if the training and testing data are collected on different days and at different locations, which is 13% higher than state-of-the-art approaches.

show abstract