無線射頻辨識(Radio Frequency Identification, RFID)技術是物理層防偽研究
領域並在無線通訊領域引起大量關注，並廣泛應用於我們的日常生活中。為了提升用戶的資訊安全，射頻指紋(RF Fingerprint)技術應運而生。此技術提取實體層訊號的射頻指紋特徵並加以識別，可以繞過可能被仿冒或竄改的設備識別標誌，如 MAC 位址或其他軟體設置。它專注於分析無線訊號的物理特性，這些特徵因設備製造時的硬體不完美特性具有強大的防偽能力，受到物聯網和 Wi-Fi 等無線傳輸領域的研究者的青睞。尤其在物聯網應用中，如智慧家電、智慧城市、工業自動化等，以及 Wi-Fi 等 5G 甚至 6G 行動網路網絡中的安全管理和訪問控制。
本論文針對 ISO 14443A 之 HF RFID 卡片進行研究，提出了基於單類別支援向量機(One-Class Support Vector Machine, OCSVM)作為異常偵測模型，並以研製之特規讀取機錄製不同廠牌的卡片訊號利用該模型進行合法卡和偽卡的辨識，再結合集成學習中之加權軟投票(Weighted soft voting, WSV)機制將不同特徵之辨識模型整合使其具有強大的防偽能力。本論文提出之方法對於保障 RFID 卡片的安全性和推動無線通訊技術的發展具有重要意義。

Radio Frequency Identification (RFID) technology has garnered significant
attention in the field of physical layer anti-counterfeiting and wireless communication. It finds widespread use in our daily lives. To enhance user information security, Radio Frequency (RF) Fingerprint technology has emerged. This technique extracts RF fingerprint features from physical layer signals and identifies them, bypassing potentially counterfeited or altered device identifiers like MAC addresses or other software settings. It focuses on analyzing the physical characteristics of wireless signals, leveraging the strong anti-counterfeiting capabilities inherent in hardware imperfections during device manufacturing. This approach is favored by researchers in wireless transmission domains such as the Internet of Things (IoT) and Wi-Fi, including applications in smart appliances, smart cities, industrial automation, as well as security management and access control in Wi-Fi, 5G, and even 6G mobile networks.
In this paper, we concentrate on ISO 14443A HF RFID cards. We propose employing the One-Class Support Vector Machine (OCSVM) as an anomaly detection model. The model is trained using recorded signals from cards of different brands captured by a custom reader. It discerns legitimate cards from counterfeit ones. Further, we enhance its anti-counterfeiting prowess by integrating various feature-specific recognition models using the Weighted Soft Voting (WSV) mechanism from ensemble learning. Our approach holds significance in safeguarding the security of RFID cards and propelling wireless communication technology.

[1] 黃昱宸, "具射頻指紋認證機制之高頻射頻辨識讀卡機研究," 碩士論文,
電機工程系, 國立臺灣科技大學, 2022. [Online]. Available:
https://hdl.handle.net/11296/6wv2j8
[2] K. Finkenzeller, RFID handbook: fundamentals and applications in
contactless smart cards, radio frequency identification and near-field
communication. John wiley & sons, 2010.
[3] 陳信豪, "ISO 14443 Type A 標籤模擬器研製," 碩士論文, 電機工程系,
國立臺灣科技大學, 2017. [Online]. Available:
https://hdl.handle.net/11296/g47dng
[4] "International standard ISO/IEC 14443 -1, -2, -3, International
Standardization Organization,April 2003."
[5] 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.
[6] 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.
[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] G. Zhang, L. Xia, S. Jia, and Y. Ji, "Physical-layer identification of HF
RFID cards based on RF fingerprinting," in Information Security Practice
and Experience: 12th International Conference, ISPEC 2016, Zhangjiajie,
China, November 16-18, 2016, Proceedings 12, 2016: Springer.
[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.
56
[12] 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: IEEE, pp. 292-300.
[13] Y. Shi and M. A. Jensen, "Improved radiometric identification of wireless
devices using MIMO transmission," IEEE Transactions on Information
Forensics and Security, vol. 6, no. 4, pp. 1346-1354, 2011.
[14] N. Soltanieh, Y. Norouzi, Y. Yang, and N. C. Karmakar, "A review of radio
frequency fingerprinting techniques," IEEE Journal of Radio Frequency
Identification, vol. 4, no. 3, pp. 222-233, 2020.
[15] Y. Lin, L. Chen, and G. Zhang, "Power Spectrum Based Wi-Fi RF
Fingerprint Extraction Method," in 2021 13th International Conference on
Measuring Technology and Mechatronics Automation (ICMTMA), 2021:
IEEE, pp. 105-109.
[16] 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.
[17] V. Vapnik, The nature of statistical learning theory. Springer science &
business media, 1999.
[18] S. Huang, N. Cai, P. P. Pacheco, S. Narrandes, Y. Wang, and W. Xu,
"Applications of support vector machine (SVM) learning in cancer
genomics," Cancer genomics & proteomics, vol. 15, no. 1, pp. 41-51, 2018.
[19] P. Tao, Z. Sun, and Z. Sun, "An improved intrusion detection algorithm
based on GA and SVM," Ieee Access, vol. 6, pp. 13624-13631, 2018.
[20] V. K. Chauhan, K. Dahiya, and A. Sharma, "Problem formulations and
solvers in linear SVM: a review," Artificial Intelligence Review, vol. 52, no.
2, pp. 803-855, 2019.
[21] M. Aljanabi, M. H. Qutqut, and M. Hijjawi, "Machine learning
classification techniques for heart disease prediction: a review,"
International Journal of Engineering & Technology, vol. 7, no. 4, pp. 5373-
5379, 2018.
[22] N. Caballé-Cervigón, J. L. Castillo-Sequera, J. A. Gómez-Pulido, J. M.
Gómez-Pulido, and M. L. Polo-Luque, "Machine learning applied to
diagnosis of human diseases: A systematic review," Applied Sciences, vol.
10, no. 15, p. 5135, 2020.
[23] Q.-Q. Tao, S. Zhan, X.-H. Li, and T. Kurihara, "Robust face detection using
local CNN and SVM based on kernel combination," Neurocomputing, vol.
211, pp. 98-105, 2016.
57
[24] S. Kumar, S. Singh, and J. Kumar, "Multiple face detection using hybrid
features with SVM classifier," in Data and Communication Networks:
Proceedings of GUCON 2018, 2019: Springer, pp. 253-265.
[25] H. Li, "Text recognition and classification of english teaching content based
on SVM," Journal of Intelligent & Fuzzy Systems, vol. 39, no. 2, pp. 1757-
1767, 2020. [Online]. Available:
https://content.iospress.com/articles/journal-of-intelligent-and-fuzzysystems/ifs179949.
[26] L. M. Francis and N. Sreenath, "TEDLESS–Text detection using leastsquare SVM from natural scene," Journal of King Saud UniversityComputer and Information Sciences, vol. 32, no. 3, pp. 287-299, 2020.
[27] S. Alla and S. K. Adari, Beginning anomaly detection using python-based
deep learning. Springer, 2019.
[28] H. Lukashevich, S. Nowak, and P. Dunker, "Using one-class SVM outliers
detection for verification of collaboratively tagged image training sets," in
2009 IEEE International Conference on Multimedia and Expo, 2009: IEEE,
pp. 682-685.
[29] Y. Li, T. Zhang, Y. Y. Ma, and C. Zhou, "Anomaly detection of user
behavior for database security audit based on ocsvm," in 2016 3rd
International Conference on Information Science and Control Engineering
(ICISCE), 2016: IEEE, pp. 214-219.
[30] E. H. Budiarto, A. E. Permanasari, and S. Fauziati, "Unsupervised anomaly
detection using K-means, local outlier factor and one class SVM," in 2019
5th international conference on science and technology (ICST), 2019, vol.
1: IEEE, pp. 1-5.
[31] 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.
[32] 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.
[33] F. Schwenker, "Ensemble methods: Foundations and algorithms [book
review]," IEEE Computational Intelligence Magazine, vol. 8, no. 1, pp. 77-
79, 2013.
[34] A. El Mekki, A. Alami, H. Alami, A. Khoumsi, and I. Berrada, "Weighted
combination of BERT and N-GRAM features for Nuanced Arabic Dialect
Identification," in Proceedings of the Fifth Arabic Natural Language
Processing Workshop, 2020, pp. 268-274.
58
[35] A. Taha, "Intelligent ensemble learning approach for phishing website
detection based on weighted soft voting," Mathematics, vol. 9, no. 21, p.
2799, 2021.
[36] L. I. Kuncheva and J. J. Rodríguez, "A weighted voting framework for
classifiers ensembles," Knowledge and information systems, vol. 38, pp.
259-275, 2014.
[37] 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:
IEEE, pp. 266-269.
[38] Y. Xiao, H. Wang, and W. Xu, "Parameter selection of Gaussian kernel for
one-class SVM," IEEE transactions on cybernetics, vol. 45, no. 5, pp. 941-
953, 2014.
[39] Y. Sai, R. Jinxia, and L. Zhongxia, "Learning of neural networks based on
weighted mean squares error function," in 2009 Second International
Symposium on Computational Intelligence and Design, 2009, vol. 1: IEEE,
pp. 241-244.
[40] 楊舒合, "基於 CNN 演算法之數位身份證射頻指紋認證研究," 碩士論
文, 電機工程系, 國立臺灣科技大學, 2022. [Online]. Available:
https://hdl.handle.net/11296/89s6b3