射頻指紋特徵(RF Fingerprint))是近年非常受關注的物理層防偽技術，藉由分析接收訊號提取特徵、直接識別硬體特性的方式，有很強的防偽能力，深受物聯網與WIFI等廣泛運用於日常之技術的研究者青睞。而無線射頻識別(Radio Frequency Identification, RFID)裝置作為市面上最常見之數位識別證，可使用之場合與功能也日漸豐富，除了大眾運輸系統通行日後或許也能進行個人資料認證等。因此對於資訊安全的要求也更高。
本論文通過國家儀器(NI)開發之NI PXIe-5641R軟體無線電平台(Software Define Radio, SDR)建立模擬讀取器與卡片進行溝通並即時提取射頻指紋特徵，再通過TCP傳送至後端由Python語言撰寫之資料庫分析系統辨別讀取卡片的真實身分。分析系統主要採用機器學習之KNNM(SVM)與CNN模型，論文中也會探討不同演算法之結合方法，以期完成在盡可能保證真卡辨識率的條件下保有未知卡片分辨功能之特規讀卡機系統。
本論文之實驗中共使用55張符合ISO 14443A規範的同廠牌之HF RFID卡片與一個固定的接收端，進行可辨別真卡與未知卡片之特規讀卡機實驗。

RF Fingerprint is a physical layer anti-counterfeiting technology that has attracted great attention in recent years. It has strong anti-counterfeiting ability by analyzing the received signal and extracting features to directly identify hardware characteristics. It is widely used in the Internet of Things and WIFI. As the most common digital identification card on the market, Radio Frequency Identification (RFID) devices can be used in more and more occasions and functions. In addition to the public transportation system, it may also perform personal data authentication in the future. Therefore, the requirements for information security are also higher than before.
This paper uses the NI PXIe-5641R software defined radio platform(SDR),which developed by National Instruments (NI) ,to establish an analog reader to communicate with the card and extract the RF fingerprint features in real time, and then transmit it to the back-end through TCP. The database analysis system identifies the true identity of the read card through Python language. The analysis system mainly uses the KNNM (SVM)and CNN models of machine learning. The paper focus on the combination of different algorithms to complete the special card reader system that retains the function of distinguishing fake cards, while ensuring the recognition rate of real cards as much as possible.
In the experiments, a total of 55 HF RFID cards of the same brand conforming to the ISO 14443A standard and a fixed receiver are used to verify of a special card reader that can distinguish the authenticity of the card.

[1] K. Finkenzeller, RFID handbook: fundamentals and applications in contactless smart cards, radio frequency identification and near-field communication. John wiley & sons, 2010.
[2] 陳信豪, "ISO 14443 Type A 標籤模擬器研製," 碩士, 電機工程系, 國立臺灣科技大學, 台北市, 2017.
[3] 陳冠儒, "ISO 14443 Type A 軟體無線電射頻辨識讀取器研製," 碩士, 電機工程系, 國立臺灣科技大學, 台北市, 2015.
[4] "International standard ISO/IEC 14443 -1, -2, -3, International Standardization Organization,April 2003."
[5] Q. Xu, R. Zheng, W. Saad, Z. J. I. C. S. Han, and Tutorials, "Device fingerprinting in wireless networks: Challenges and opportunities," IEEE Communications Surveys Tutorials, vol. 18, no. 1, pp. 94-104, 2015.
[6] M. F. Bari, P. Agrawal, B. Chatterjee, and S. J. a. p. a. Sen, "Statistical Analysis Based Feature Selection Enhanced RF-PUF with> 99.8% Accuracy on Unmodified Commodity Transmitters for IoT Physical Security," arXiv preprint arXiv:.05684, 2022.
[7] H. P. Romero, K. A. Remley, D. F. Williams, and C.-M. Wang, "Electromagnetic measurements for counterfeit detection of radio frequency identification cards," IEEE Transactions on Microwave Theory Techniques, vol. 57, no. 5, pp. 1383-1387, 2009.
[8] H. P. Romero, K. A. Remley, D. F. Williams, C.-M. Wang, and T. X. Brown, "Identifying RF identification cards from measurements of resonance and carrier harmonics," IEEE Transactions on Microwave Theory Techniques, vol. 58, no. 7, pp. 1758-1765, 2010.
[9] B. Danev, S. Capkun, R. Jayaram Masti, and T. S. Benjamin, "Towards practical identification of HF RFID devices," ACM transactions on Information System Security, vol. 15, no. 2, pp. 1-24, 2012.
[10] A. Mehmood, W. Aman, M. M. U. Rahman, M. A. Imran, and Q. H. Abbasi, "Preventing Identity Attacks in RFID Backscatter Communication Systems: A Physical-layer Approach," in 2020 International Conference on UK-China Emerging Technologies (UCET), 2020, pp. 1-5: IEEE.
[11] G. Zhang, L. Xia, S. Jia, and Y. Ji, "Identification of cloned HF RFID proximity cards based on RF fingerprinting," in 2016 IEEE Trustcom/BigDataSE/ISPA, 2016, pp. 292-300: IEEE.
[12] 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, pp. 284-299: Springer.
[13] W. Lee, S. Y. Baek, and S. H. J. I. C. M. Kim, "Deep-Learning-Aided RF Fingerprinting for NFC Security," IEEE Communications Magazine, vol. 59, no. 5, pp. 96-101, 2021.
[14] G. Guo, H. Wang, D. Bell, Y. Bi, and K. Greer, "KNN model-based approach in classification," in OTM Confederated International Conferences" On the Move to Meaningful Internet Systems", 2003, pp. 986-996: Springer.
[15] C. Yunqiang, Z. Xiang Sean, and T. S. Huang, "One-class SVM for learning in image retrieval," in Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001, vol. 1, pp. 34-37 vol.1.
[16] S. Wang, L. Peng, H. Fu, A. Hu, and X. Zhou, "A convolutional neural network-based RF fingerprinting identification scheme for mobile phones," in IEEE INFOCOM 2020-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2020, pp. 115-120: IEEE.
[17] G. Shen, J. Zhang, A. Marshall, L. Peng, and X. Wang, "Radio frequency fingerprint identification for LoRa using spectrogram and CNN," in IEEE INFOCOM 2021-IEEE Conference on Computer Communications, 2021, pp. 1-10: IEEE.
[18] O. Sagi, L. J. W. I. R. D. M. Rokach, and K. Discovery, "Ensemble learning: A survey," Wiley Interdisciplinary Reviews: Data Mining Knowledge Discovery, vol. 8, no. 4, p. e1249, 2018.
[19] X. Dong, Z. Yu, W. Cao, Y. Shi, and Q. J. F. o. C. S. Ma, "A survey on ensemble learning," Frontiers of Computer Science, vol. 14, no. 2, pp. 241-258, 2020.
[20] R. N. D. Ranasinghe and G. Z. Yu, "RFID/NFC device with embedded fingerprint authentication system," in 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), 2017, pp. 266-269: IEEE.
[21] R. M. Haralick, "Digital step edges from zero crossing of second directional derivatives," in Readings in Computer Vision: Elsevier, 1987, pp. 216-226.
[22] S. Bernhart, E. Leitgeb, G. A. Hofbauer, and U. Feichter, "Rising edge detection used as TOA estimator for mode S signals with multipath propagation," in 2017 25th International Conference on Software, Telecommunications and Computer Networks (SoftCOM), 2017, pp. 1-6: IEEE