透過您的圖書館登入
IP:3.215.16.238
  • Journals

基於深度學習之無線電硬體特徵識別邊緣運算架構

Deep Learning based Wireless Radio Identification Architecture for Edge Computing

Abstracts


隨著近距離無線通訊(Near-field Communication)的普及,門禁設備的攻擊以及防禦也備受關注,然而目前市面上的不少電子門禁系統的身分驗證機制仍舊是基於門禁卡片的UID(Unique Identifier)進行身分識別。近年來已有相關研究成果指出,透過硬體元件之間的差異性,可有效識別出不同的裝置設備指紋(Device Fingerprinting),以此間接判斷使用者的合法性,以提高無線電通訊設備的資訊安全。為了解決門禁裝置身分識別上的風險,本研究使用軟體定義無線電收取NFC頻段訊號,提取I/Q訊號樣本當作特徵,利用卷積神經網路(Convolution Neural Network,CNN),將提取到的無線電裝置設備的特徵交由人工智慧進行學習建立模型的方法,進一步結合邊緣運算(Edge Computing)的架構,驗證識別NFC卡片複製攻擊(Clone Attack)的可行性。

Parallel abstracts


With the popularity of Near-field Communication(NFC), attacks and defenses of access control systems have also attracted much attention. However, the identity verification of many commercial electronic access control systems at present is still based on the Unique Identifier (UID) of the access control card for identity identification. In recent years, the literature shows the difference between hardware components can effectively identify different device fingerprinting, thereby indirectly judging the legitimacy of the user, to improve the information security of radio communication equipment. To solve the risk of identification of access control devices, the software-defined radio is used to collect NFC band signals to extract I/Q signal samples as features in the study. The extracted radio device features are handed to learn and build a model, and further combined with the Edge Computing architecture to verify and identify NFC card replication.

References


Steve Boggan, “‘Fakeproof’ e-passport is cloned in minutes.” The Times, 6 August 2008, Available: https://www.thetimes.co.uk/article/fakeproof-e-passport-is-cloned-in-minutes-9h7jscpsbr8
“MIFARE Classic EV1 1K – Mainstream contactless smart card IC for fast and easy solution development," [Online]. Available: https://www.nxp.com/docs/en/data-sheet/MF1S50YYX_V1.pdf
"Near Field Communication (NFC) Technology and Measurements White Paper" Available: https://cdn.rohde-schwarz.com/pws/dl_downloads/dl_application/application_notes/1ma182/1MA182_5E_NFC_WHITE_PAPER.pdf
H. Jafari, O. Omotere, D. Adesina, H. Wu, and L. Qian. IoT devices fin gerprinting using deep learning. In 2018 IEEE Military Communications Conference (MILCOM), pages 1-9, 2018.
V. Brik et al., "Wireless Device Identification with Radiometric Signatures," Proceedings of the 14th Annual International Conference on Mobile Computing and Networking, MOBICOM 2008, pp. 116-27, 2008.

Read-around