Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

RF Fingerprinting Scheme for Authenticating 433MHz Band Transmitters

433 MHz 대역 송신기의 인증을 위한 RF 지문 기법

  • Young Min, Kim (Computer Team, Kangrim Heavy industry) ;
  • Woongsup, Lee (Department of Information Engineering, Gyeongsang National University) ;
  • Seong Hwan, Kim (Major of Data Science, Korea National University of Transportation)
  • Received : 2022.11.26
  • Accepted : 2022.12.11
  • Published : 2023.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Small communication devices used in the Internet of Things are vulnerable to various hacking because they do not apply advanced encryption techniques due to their low memory capacity or slow computation speed. In order to increase the authentication reliability of small-sized transmitters operating in 433MHz band, we introduce an RF fingerprint and adopt a convolutional neural network (CNN) as a classification algorithm. The preamble signal transmitted by each transmitter are extracted and collected using software-defined-radio to constitute a training data set, which is used for training the CNN. We tested identification of 20 transmitters in four different scenarios and obtained high identification accuracy. In particular, the accuracy of 95.8% and 92.6% was obtained, respectively in the scenario where the test was performed at a location different from the transmitter's location at the time of collecting training data, and in the scenario where the transmitter moves at walking speed.

사물인터넷에 사용되는 소형 통신 기기들은 적은 메모리 용량과 느린 연산 속도 때문에 고급 암호기법을 적용하지 못하기 때문에 각종 해킹에 취약하다. 본 논문은 433MHz 대역에서 동작하는 소형 송신기들의 인증 신뢰도를 높이기 위해 RF지문을 도입하고 분류 알고리즘으로 CNN (convolutional neural network) 을 사용한다. 각 송신기가 전송하는 프리엠블 신호를 소프트웨어정의라디오를 사용하여 추출하고 수집하여 학습 데이터 집합으로 만들고, 이를 신경망을 학습시키는 데에 사용한다. 네 가지의 시나리오에서 20개의 송신기의 식별을 테스트한 결과 높은 식별 정확도를 얻을 수 있었다. 특히 학습 데이터 수집 시의 위치와 다른 위치에서 테스트를 수행한 시나리오에서, 그리고 송신기가 걷는 속도로 이동하는 시나리오에서 각각 95.8%, 92.6%의 정확도를 산출함을 알 수 있었다.

Keywords

Acknowledgement

This was supported by Korea National University of Transportation in 2021.

References

  1. H. Han and D. Park, "Cybersecurity of The Defense Information System network connected IoT Sensors," Journal of the Korea Institute of Information and Communication Engineering, vol. 24, no. 6, pp. 802-808, Jun. 2020. DOI: 10.6109/jkiice.2020.24.6.802.
  2. F. D. Garcia, D. Oswald, T. Kasper, and P. Pavlides, "Lock it and still lose it-on the (in)security of automotive remote keyless entry systems," in Proceeding of 25th USENIX security symposium, Austin: TX, USA, pp. 929-944, 2016.
  3. O. Ureten and N. Serinken. "Wireless security through RF fingerprinting," Canadian Journal of Electrical and Computer Engineering, vol. 32, no. 1, pp. 27-33, 2007. DOI: 10.1109/CJECE.2007.364330.
  4. B. Danev, T. S. Heydt-Benjamin, and S. Capkun, "Physical-layer identification of RFID devices," in Proceeding of USENIX security symposium, Montreal: QC, Canada, Aug. 2009.
  5. A. M. Ali, E. Uzundurukan, and A. Kara, "Assessment of Features and Classifiers for Bluetooth RF Fingerprinting," IEEE Access, vol. 7, pp. 50524-50535, Apr. 2019. DOI: 10.1109/ACCESS.2019.2911452.
  6. 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, Feb. 2018. DOI: 10.1109/JSTSP.2018.2796446.
  7. J. Yu, A. Hu, G. Li, and L. Peng, "A Robust RF Fingerprinting Approach Using Multisampling Convolutional Neural Network," IEEE Internet of Things Journal, vol. 6, no. 4, pp. 6486-6799, Aug. 2019. DOI: 10.1109/JIOT.2019.2911347.
  8. S. Wang, L. Peng, H. Fu, A. Hu, and X. Zhou, "A Convolutional Neural Network-Based RF Fingerprinting Identification Scheme for Mobile Phones," in Proceeding of the IEEE International Conference on Computer Communications, Toronto: ON, Canada, Jul. 2020. DOI: 10.1109/INFOCOMWKSHPS50562.2020.9163058.
  9. T. Jian, B. C. Rendon, E. Ojuba, N. Wang, K. Sankhe, A. Gritsenko, J. Dy, K. Chowdhury, and S. Ioannidis, "Deep Learning for RF Fingerprinting: A Massive Experimental Study," IEEE Internet of Things Magazine, vol. 3, no. 1, pp. 50-57, Mar. 2020. DOI: 10.1109/IOTM.0001.1900065.
  10. 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, May 2021. DOI: 10.1109/MCOM.001.2000912.
  11. Y. M. Kim, Y. M. Bak, W. Lee, and S. H. Kim, "Authentication Mechanism for 433MHz band Transceiver Module using Deep learning based RF Fingerprinting," in Proceedings of the 2019 Fall Conference of the Korea Information and Communications, Busan, Korea, pp. 397-399, 2019.
  12. Y. M. Kim, "Physical-layer schemes to enhance the reliability of authentication for IoT devices," M. S. thesis, Gyeongsang National University, Korea, 2020.
  13. I. J. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, MA: USA, 2016.