Wifi Device Identification through Neural Network based on Channel State Information

Li-Hsien Lin ； Hsin-Hung Cho ； Chi-Yuan Chen

《資訊安全通訊》 26卷4期 (2020/12) Pp. 34-47

摘要

The tremendous growth of wireless networks has brought a great deal of convenient to our daily lives. But the wireless devices are vulnerable to several attacks such as unauthorized client access. Therefore we want to be able to identify the legitimate and malicious Access Point (AP) for security purpose. The malicious user may attempt to apply attacks such as ARP attack, a method to change the ARP table to get legitimate user's data, Evil twin attack or Rouge AP, the attacker imitates the SSID as the legitimate Wifi AP to misleading the user to connect to the malicious APs. It will be a challenge to recognize the difference between legitimate AP and malicious AP when they have exactly same SSID and MAC address. This paper proposed a method to identity the Wifi APs through physical characteristics. The experiment is performed as a supervised learning LSTM and RNN based on Channel State Information (CSI). Comparing between LSTM and RNN, the results show that LSTM architecture is able to perform a better classification than RNN.

關鍵字

Channel State Information ； Wifi AP Identification ； Machine Learning ； Neural Network

參考文獻

R. Das, A. Gadre, S. Zhang, S. Kumar and J. M. F. Moura, ”A Deep Learning Approach to IoT Authentication,” 2018 IEEE International Conference on Communications (ICC), Kansas City, MO, 2018, pp. 1-6, doi: 10.1109/ICC.2018.8422832.

S. Riyaz, K. Sankhe, S. Ioannidis and K. Chowdhury, ”Deep Learning Convolutional Neural Networks for Radio Identification,” in IEEE Communications Magazine, vol. 56, no. 9, pp. 146-152, Sept. 2018, doi: 10.1109/MCOM.2018.1800153.

V. L. L. Thing, ”IEEE 802.11 Network Anomaly Detection and Attack Classification: A Deep Learning Approach,” 2017 IEEE Wireless Communications and Networking Conference (WCNC), San Francisco, CA, 2017, pp. 1-6, doi: 10.1109/WCNC.2017.7925567.

K. Merchant, S. Revay, G. Stantchev and B. Nousain, ”Deep Learning for RF Device Fingerprinting in Cognitive Communication Networks,” in IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 1, pp. 160-167, Feb. 2018, doi: 10.1109/JSTSP.2018.2796446.

H. Weng, X. Dong, X. Hu, D. G. Beetner, T. Hubing and D. Wunsch, ”Neural network detection and identification of electronic devices based on their unintended emissions,” 2005 International Symposium on Electromagnetic Compatibility, 2005. EMC 2005., Chicago, IL, 2005, pp. 245-249 Vol. 1, doi: 10.1109/ISEMC.2005.1513508.