ABSTRACT
Physical-layer fingerprinting investigates how features extracted from radio signals can be used to uniquely identify devices. This paper proposes and analyses a novel methodology to fingerprint LoRa devices, which is inspired by recent advances in supervised machine learning and zero-shot image classification. Contrary to previous works, our methodology does not rely on localized and low-dimensional features, such as those extracted from the signal transient or preamble, but uses the entire signal. We have performed our experiments using 22 LoRa devices with 3 different chipsets. Our results show that identical chipsets can be distinguished with 59% to 99% accuracy per symbol, whereas chipsets from different vendors can be fingerprinted with 99% to 100% accuracy per symbol. The fingerprinting can be performed using only inexpensive commercial off-the-shelf software defined radios, and a low sample rate of 1 Msps. Finally, we release all datasets and code pertaining to these experiments to the public domain.
- Martin Abadi, Ashish Agarwal, and others. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016).Google Scholar
- Vladimir Brik, Suman Banerjee, Marco Gruteser, and Sangho Oh. 2008. Wireless device identification with radiometric signatures. In Proc. 14th Int. Conf. Mobile computing and networking. ACM, 116--127. Google ScholarDigital Library
- Chih-Chung Chang and Chih-Jen Lin. 2011. LIBSVM: a library for support vector machines. Trans. on Intelligent Systems and Technology (TIST) 2, 3 (2011), 27. Google ScholarDigital Library
- Boris Danev and Srdjan Capkun. 2009. Transient-based identification of wireless sensor nodes. In Proc. 2009 Int. Conf. on Information Processing in Sensor Networks. IEEE Computer Society, 25--36. Google ScholarDigital Library
- Boris Danev, Srdjan Capkun, Ramya Jayaram Masti, and Thomas S. Benjamin. 2012. Towards practical identification of HF RFID devices. Trans. on Information and System Security (TISSEC) 15, 2, Article 7 (July 2012), 24 pages. Google ScholarDigital Library
- Boris Danev, Thomas S. Heydt-Benjamin, and Srdjan Čapkun. 2009. Physical-layer Identification of RFID Devices. In Proc. 18th Conf. on USENIX Security Symposium (SSYM'09). USENIX Association, Berkeley, CA, USA, 199--214. Google ScholarDigital Library
- Boris Danev, Heinrich Luecken, Srdjan Capkun, and Karim El Defrawy. 2010. Attacks on physical-layer identification. In Proc. 3rd Conf. on Wireless network security. ACM, 89--98. Google ScholarDigital Library
- Boris Danev, Davide Zanetti, and Srdjan Capkun. 2012. On physical-layer identification of wireless devices. Computing Surveys (CSUR) (2012). Google ScholarDigital Library
- Martin Ester, Hans-Peter Kriegel, Jörg Sander, Xiaowei Xu, and others. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise.. In Kdd, Vol. 96. 226--231. Google ScholarDigital Library
- Jinsong Han, Chen Qian, Panlong Yang, Dan Ma, Zhiping Jiang, Wei Xi, and Jizhong Zhao. 2016. Geneprint: generic and accurate physical-layer identification for UHF RFID tags. IEEE/ACM Trans. on Networking 24, 2 (2016), 846--858. Google ScholarDigital Library
- Marti A. Hearst, Susan T Dumais, Edgar Osuna, John Platt, and Bernhard Scholkopf. 1998. Support vector machines. IEEE Intelligent Systems and their Applications 13, 4 (1998), 18--28. Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems. 1097--1105. Google ScholarDigital Library
- Christoph H Lampert, Hannes Nickisch, and Stefan Harmeling. 2014. Attribute-based classification for zero-shot visual object categorization. IEEE Trans. on Pattern Analysis and Machine Intelligence 36, 3 (2014), 453--465. Google ScholarDigital Library
- Hugo Larochelle, Dumitru Erhan, and Yoshua Bengio. 2008. Zero-data Learning of New Tasks. In Proc. 23rd Nat. Conf. on Artificial Intelligence. 646--651. Google ScholarDigital Library
- Yao Lu. 2015. Unsupervised Learning on Neural Network Outputs. CoRR abs/1506.00990 (2015).Google Scholar
- Aaron Van den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu. 2016. Pixel Recurrent Neural Networks. In Proc. 33rd Int. Conf. on Machine Learning. Google ScholarDigital Library
- C David Page and Sriraam Natarajan. 2014. Encyclopedia of Machine Learning and Data Mining. 2 (2014), 1--24.Google Scholar
- F. Pedregosa, G. Varoquaux, and others. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825--2830. Google ScholarDigital Library
- Benjamin W. Ramsey, Stubbs, and others. 2015. Wireless infrastructure protection using low-cost radio frequency fingerprinting receivers. Int. Journal of Critical Infrastructure Protection 8 (2015), 27--39. Google ScholarDigital Library
- Benjamin W Ramsey, Michael A Temple, and Barry E Mullins. 2012. PHY foundation for multi-factor ZigBee node authentication. In Global Communications Conference (GLOBECOM). IEEE, 795--800.Google ScholarCross Ref
- K. Bonne Rasmussen and S. Capkun. 2007. Implications of radio fingerprinting on the security of sensor networks. In Proc. 3th. Int. Conf. Security and Privacy in Communications Networks and the Workshops - SecureComm. 331--340.Google Scholar
- Saeed Ur Rehman, Kevin Sowerby, and Colin Coghill. 2012. RF fingerprint extraction from the energy envelope of an instantaneous transient signal. In Communications Theory Workshop (AusCTW), 2012 Australian. IEEE, 90--95.Google ScholarCross Ref
- KA Remley, CA Grosvenor, RT Johnk, DR Novotny, PD Hale, MD McKinley, A Karygiannis, and E Antonakakis. 2005. Electromagnetic signatures of WLAN cards and network security. In Proc. 5th IEEE Int. Symposium on Signal Processing and Information Technology. IEEE, 484--488.Google ScholarCross Ref
- Karen Simonyan, Sander Dieleman, Andrew Senior, and Alex Graves. 2016. WaveNet: A Generative Model for Raw Audio. (2016), 1--15.Google Scholar
- Richard Socher, Milind Ganjoo, Christopher D Manning, and Andrew Ng. 2013. Zero-shot learning through cross-modal transfer. In Advances in Neural Information Processing Systems. 935--943. Google ScholarDigital Library
- N Sornin, M Luis, T Eirich, T Kramp, and O Hersent. 2015. LoRaWAN™ Specifications. LoRa™ Alliance (2015).Google Scholar
- Christian Szegedy, Wei Liu, and others. 2015. Going deeper with convolutions. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition. 1--9.Google ScholarCross Ref
- Tien Dang Vo-Huu, Triet Dang Vo-Huu, and Guevara Noubir. 2016. Fingerprinting Wi-Fi Devices Using Software Defined Radios. In Proc. 9th Conf. Security & Privacy in Wireless and Mobile Networks. ACM, 3--14. Google ScholarDigital Library
Index Terms
- Physical-layer fingerprinting of LoRa devices using supervised and zero-shot learning
Recommendations
Fingerprinting IoT Devices Using Latent Physical Side-Channels
The proliferation of low-end low-power internet-of-things (IoT) devices in "smart" environments necessitates secure identification and authentication of these devices via low-overhead fingerprinting methods. Previous work typically utilizes ...
Big Data fingerprinting information analytics for sustainability
AbstractWeb-based device fingerprinting is the process of collecting security information through the browser to perform stateless device identification. Fingerprints may then be used to identify and track computing devices in the web. There are various ...
Highlights- Available approaches to web tracking mechanism are analyzed in this paper.
- Big data fingerprinting for sustainability is extensively discussed.
- Achievements and developments in big data fingerprinting discovery and exploration are ...
A Novel Polymorphic Gate Based Circuit Fingerprinting Technique
GLSVLSI '18: Proceedings of the 2018 on Great Lakes Symposium on VLSIPolymorphic gates are reconfigurable devices that deliver multiple functionalities at different temperature, supply voltage or external inputs. Capable of working in different modes, polymorphic gate is a promising candidate for embedding secret ...
Comments