A Deep Learning Approach to IoT Authentication

At its peak, the Internet-of-Things will largely be composed of low-power devices with wireless radios attached. Yet, secure authentication of these devices amidst adversaries with much higher power and computational capability remains a challenge, even for advanced cryptographic and wireless security protocols. For instance, a high-power software radio could simply replay chunks of signals from a low-power device to emulate it. This paper presents a deep-learning classifier that learns hardware imperfections of low-power radios that are challenging to emulate, even for high- power adversaries. We build an LSTM framework, specifically sensitive to signal imperfections that persist over long durations. Experimental results from a testbed of 30 low-power nodes demonstrate high resilience to advanced software radio adversaries.

[1]  Dennis Goeckel,et al.  Identifying Wireless Users via Transmitter Imperfections , 2011, IEEE Journal on Selected Areas in Communications.

[2]  Mohamed Elkhidir,et al.  FPGA based implementation of elliptic curve cryptography , 2015, 2015 World Symposium on Computer Networks and Information Security (WSCNIS).

[3]  Marimuthu Palaniswami,et al.  Internet of Things (IoT): A vision, architectural elements, and future directions , 2012, Future Gener. Comput. Syst..

[4]  Larry J. Greenstein,et al.  A Physical-Layer Technique to Enhance Authentication for Mobile Terminals , 2008, 2008 IEEE International Conference on Communications.

[5]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[6]  Abbas Jamalipour,et al.  Wireless communications , 2005, GLOBECOM '05. IEEE Global Telecommunications Conference, 2005..

[7]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[8]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[9]  T. Mehmood,et al.  Speech recognition using multilayer perceptron , 2002, IEEE Students Conference, ISCON '02. Proceedings..

[10]  Stefan C. Kremer,et al.  Recurrent Neural Networks , 2013, Handbook on Neural Information Processing.

[11]  Swarun Kumar,et al.  Guaranteeing spoof-resilient multi-robot networks , 2015, Auton. Robots.

[12]  Zhi Chen,et al.  A lightweight attribute-based encryption scheme for the Internet of Things , 2015, Future Gener. Comput. Syst..

[13]  Jie Xiong,et al.  SecureArray: improving wifi security with fine-grained physical-layer information , 2013, MobiCom.

[14]  Stephen Grossberg,et al.  Recurrent neural networks , 2013, Scholarpedia.

[15]  Yacine Challal,et al.  C-CP-ABE: Cooperative Ciphertext Policy Attribute-Based Encryption for the Internet of Things , 2014, 2014 International Conference on Advanced Networking Distributed Systems and Applications.

[16]  Athanasios V. Vasilakos,et al.  Mobile Cloud Computing: A Survey, State of Art and Future Directions , 2013, Mobile Networks and Applications.

[17]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[18]  Fang Liu,et al.  Location-aware key establishment in wireless sensor networks , 2006, IWCMC '06.

[19]  Brian M. Sadler,et al.  MIMO Authentication via Deliberate Fingerprinting at the Physical Layer , 2011, IEEE Transactions on Information Forensics and Security.

[20]  Christoph Neumann,et al.  An Empirical Study of Passive 802.11 Device Fingerprinting , 2012, 2012 32nd International Conference on Distributed Computing Systems Workshops.

[21]  Marco Gruteser,et al.  Wireless device identification with radiometric signatures , 2008, MobiCom '08.