射頻指紋(Radio Frequency Fingerprint , RFF)辨識已成為近期研究議題，通過學習和提取傳輸信號中因傳送端硬體差異而對訊號產生的獨特特徵進行辨識，來增加無線網路和通訊的安全性。無線射頻辨識(Radio Frequency Identification, RFID)卡片為近距離非接觸式智慧卡(Proximity Cards)，已普遍被應用在生活中，除了最常見作為大眾交通運輸通勤所使用，另外也更多應用在身份認證上，透過提取每張卡片的獨特特徵，因其射頻特徵難以偽造，因此能進行傳送端的辨識。
結合深度學習的辨識方法已成為近期射頻指紋辨識的趨勢，在不需另外設計特徵工程(Feature Engineering)辨識的情況下，使用機器學習自動學習提取之訊號特徵進行傳送端辨識與驗證。以往深度學習方法的一個挑戰是它們僅識別先前在訓練集中觀察到的設備：如果來自未見過的新設備通過分類器，則會被分類為已知設備之一。
本論文以ISO 14443A之HF RFID卡片，透過一接收端錄製不同廠牌與相同廠牌之訊號，結合本論文提出的方法，使用卷積神經網路(Convolution Neural Network, CNN)作為特徵提取器，提取射頻指紋特徵以及支援向量描述域(Support vector domain description , SVDD)作為異常偵測模型，將看過的資料映射到一超球體中，找到一個中心，半徑最小的球面邊界，實現對未知數據的分類。論文提出之方法可進行真偽的辨識，且能在未知資料標籤的情況下進行辨識，更符合實際應用的情況。

Radio Frequency Fingerprint (RFF) identification has become a recent research topic. It can improve the security of wireless network and communication by learning and extracting the unique characteristics of the transmitted signal due to the difference of the hardware of the transmitting end.
Radio frequency identification card is a short-range contactless smart card, which has been widely used in daily life. In addition to being most commonly used for public transportation and commuting, it is also more used in identity authentication. By extracting the unique characteristics of each card , because its radio frequency characteristics are difficult to forge, so it can identify the transmitting end.
The identification method combined with deep learning has become the trend of RF fingerprint identification in the near future. Without the need to design feature engineering identification, the signal features extracted by machine learning are automatically learned for the identification and verification of the transmitter.
A challenge with previous deep learning methods is that they only identify devices that were previously observed in the training set.If a new data from an unseen device is passed through the classifier, it is classified as one of the known devices.
In this paper, the ISO 14443A HF RFID card is used to record the signals of different brands and the same brand through a receiver. Combined with the method proposed in this paper, the convolutional neural network is used as a feature extractor to extract RF fingerprint features and support vectors. The description domain is used as an anomaly detection model, which maps the seen data to a hypersphere, finds a spherical boundary with the center and the smallest radius, and realizes the classification of unknown data.
The method proposed in the paper can be used to identify the authenticity and can be identified in the case of unknown data labels, which is more in line with the actual application.

[1] "International standard ISO/IEC 14443 -1, -2, -3, International Standardization Organization,April 2003.".
[2] J. M. Hamamreh, H. M. Furqan, and H. Arslan, "Classifications and applications of physical layer security techniques for confidentiality: A comprehensive survey," IEEE Communications Surveys & Tutorials, vol. 21, no. 2, pp. 1773-1828, 2018.
[3] P. Scanlon, I. O. Kennedy, and Y. Liu, "Feature extraction approaches to RF fingerprinting for device identification in femtocells," Bell Labs Technical Journal, 2010.
[4] S. Wang, H. Jiang, X. Fang, Y. Ying, J. Li, and B. Zhang, "Radio frequency fingerprint identification based on deep complex residual network," IEEE Access, 2020.
[5] Q. Xu, R. Zheng, W. Saad, and Z. Han, "Device fingerprinting in wireless networks: Challenges and opportunities," IEEE Communications Surveys & Tutorials, 2015.
[6] K. Ellis and N. Serinken, "Characteristics of radio transmitter fingerprints," Radio Science, vol. 36, no. 4, pp. 585-597, 2001.
[7] M. Barbeau, J. Hall, and E. Kranakis, "Detection of rogue devices in bluetooth networks using radio frequency fingerprinting," in proceedings of the 3rd IASTED International Conference on Communications and Computer Networks, CCN, 2006.
[8] O. Üreten and N. Serinken, "Detection of radio transmitter turn-on transients," in Electronics Letters, 1999.
[9] R. M. Gerdes, T. E. Daniels, M. Mina, and S. Russell, "Device Identification via Analog Signal Fingerprinting: A Matched Filter Approach," in NDSS, 2006.
[10] G. Zhang, L. Xia, S. Jia, and Y. Ji, "Physical-layer identification of HF RFID cards based on RF fingerprinting," in International Conference on Information Security Practice and Experience, 2016.
[11] W. Lee, S. Y. Baek, and S. H. Kim, "Deep-Learning-Aided RF Fingerprinting for NFC Security," IEEE Communications Magazine, vol. 59, no. 5, pp. 96-101, 2021.
[12] G. Zhang, L. Xia, S. Jia, and Y. Ji, "Identification of cloned HF RFID proximity cards based on RF fingerprinting," 2016.
[13] S. Wang, H. Jiang, X. Fang, Y. Ying, J. Li, and B. Zhang, "Radio frequency fingerprint identification based on deep complex residual network," IEEE Access, vol. 8, pp. 204417-204424, 2020.
[14] S. Riyaz, K. Sankhe, S. Ioannidis, and K. Chowdhury, "Deep learning convolutional neural networks for radio identification," IEEE Communications Magazine, vol. 56, no. 9, pp. 146-152, 2018.
[15] T. Jian et al., "Deep learning for RF fingerprinting: A massive experimental study," IEEE Internet of Things Magazine, vol. 3, no. 1, pp. 50-57, 2020.
[16] K. Merchant, S. Revay, G. Stantchev, and B. Nousain, "Deep learning for RF device fingerprinting in cognitive communication networks," IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 1, pp. 160-167, 2018.
[17] G. Shen, J. Zhang, A. Marshall, and J. R. Cavallaro, "Towards scalable and channel-robust radio frequency fingerprint identification for LoRa," IEEE Transactions on Information Forensics and Security, vol. 17, pp. 774-787, 2022.
[18] W. Gong et al., "A novel deep learning method for intelligent fault diagnosis of rotating machinery based on improved CNN-SVM and multichannel data fusion," Sensors, vol. 19, 2019.
[19] I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. MIT press, 2016.
[20] S. V. Radhakrishnan, A. S. Uluagac, and R. Beyah, "GTID: A technique for physical device and device type fingerprinting," IEEE Transactions on Dependable and Secure Computing, vol. 12, no. 5, pp. 519-532, 2014.
[21] P. Shi, G. Li, Y. Yuan, and L. Kuang, "Outlier detection using improved support vector data description in wireless sensor networks," Sensors, vol. 19, no. 21, p. 4712, 2019.
[22] C. Liu and K. Gryllias, "A semi-supervised Support Vector Data Description-based fault detection method for rolling element bearings based on cyclic spectral analysis," Mechanical Systems and Signal Processing, vol. 140, 2020.
[23] C. Liu and K. Gryllias, "A Deep Support Vector Data Description Method for Anomaly Detection in Helicopters," in PHM Society European Conference, 2021.
[24] J. Padilla, P. Padilla, J. Valenzuela-Valdés, J. Ramírez, and J. Górriz, "RF fingerprint measurements for the identification of devices in wireless communication networks based on feature reduction and subspace transformation," Measurement, vol. 58, pp. 468-475, 2014.