ABSTRACT
With a rapid increase in the usage of wearable IoT devices such as a smartwatch, we can easily monitor various user activities which exhibit distinct patterns for each individual. Such activities as arm swings while walking orgait, can be used to distinctly identify different users. Therefore, this indirect interaction between the users and wearable IoT devices can be used as a biometric authentication technique to seamlessly authenticate and identify users. Thus, various gait-based authentication frameworks using sensor data collected through wearable or hand-held devices were proposed in the literature. However, many of them limitedly utilized the unique patterns by extracting features from the data sequences. Moreover, they require users to walk long period of time to collect large volume of sensor data in each authentication process, which hinders prompt user authentication. To address the limitations, we propose a gait-based seamless authentication framework using deep neural network (Deep Gait). Unlike many of the existing works, Deep Gait authenticates users without any feature extraction process, which can capture the overlooked features in the existing works. Moreover, Deep Gait requires less amount of sensor data (only one walk cycle) than the existing works (8 to 20 walk cycles) for user authentication, which enables seamless access control. Our experimental results evaluated on the commercial smartwatch show that Deep Gait achieves an Equal Error Rate (EER) of 1.8% which is lower than the existing works.
- Brain, G. Tensorflow, Nov 2015. Retrieved Jan 2, 2019 from https://github.com/tensorflow/tensorflow.Google Scholar
- Cola, G., Avvenuti, M., Musso, F., and Vecchio, A. Gait-based authentication using a wrist-worn device. In Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (New York, NY, USA, November 2016), MOBIQUITOUS 2016, ACM, pp. 208--217.Google Scholar
- Draper, S. Wearable device sales will grow 26 percent worldwide in 2019, says research company gartner, December 2018. Retrieved Feb 1, 2019 from https://www.wearable-technologies.com/2018/12/wearable-device-saleswill- grow-26-percent-worldwide-in-2019-says-research-company-gartner/.Google Scholar
- Gafurov, D., Snekkenes, E., and Bours, P. Spoof attacks on gait authentication system. IEEE Transactions on Information Forensics and Security 2, 3 (Sept 2007), 491--502. Google ScholarDigital Library
- Giorgi, G., Martinelli, F., Saracino, A., and Sheikhalishahi, M. Walking through the deep: Gait analysis for user authentication through deep learning: 33rd ifip tc 11 international conference, sec 2018, held at the 24th ifip world computer congress,wcc 2018, poznan, poland, september 18--20, 2018, proceedings. pp. 62--76.Google Scholar
- Glorot, X., and Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (13--15 May 2010), vol. 9 of Proceedings of Machine Learning Research, PMLR, pp. 249--256.Google Scholar
- Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. The weka data mining software: An update. SIGKDD Explor. Newsl. 11, 1 (Nov. 2009), 10--18. Google ScholarDigital Library
- Johnston, A. H., and Weiss, G. M. Smartwatch-based biometric gait recognition. In 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS) (Sept 2015), pp. 1--6.Google ScholarCross Ref
- Kingma, D., and Ba, J. Adam: A method for stochastic optimization. International Conference on Learning Representations (12 2014).Google Scholar
- MacQueen, J. Some methods for classification and analysis of multivariate observations. In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics (1967), University of California Press, pp. 281--297.Google Scholar
- Mahfouz, A., Mahmoud, T. M., and Sharaf Eldin, A. Poster: A behavioral biometric authentication framework on smartphones. In Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security (New York, NY, USA, April 2017), ASIA CCS '17, ACM, pp. 923--925. Google ScholarDigital Library
- Muaaz, M., and Mayrhofer, R. Smartphone-based gait recognition: From authentication to imitation. IEEE Transactions on Mobile Computing 16, 11 (Nov 2017), 3209--3221.Google ScholarCross Ref
- Nair, V., and Hinton, G. E. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on International Conference on Machine Learning (2010), ICML'10, pp. 807--814. Google ScholarDigital Library
- Rawlinson, K. Hp study reveals smartwatches vulnerable to attack, July 2015. http://www8.hp.com/us/en/hp-news/press-release.html?id=2037386.Google Scholar
- Savitzky, A., and Golay, M. J. E. Smoothing and differentiation of data by simplified least squares procedures. Analytical Chemistry 36, 8 (1964), 1627--1639.Google ScholarCross Ref
- Shahzad, M., Liu, A. X., and Samuel, A. Secure unlocking of mobile touch screen devices by simple gestures: You can see it but you can not do it. In Proceedings of the 19th Annual International Conference on Mobile Computing & Networking (New York, NY, USA, 2013), MobiCom '13, ACM, pp. 39--50.Google ScholarDigital Library
- Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1 (Jan. 2014), 1929--1958.Google ScholarDigital Library
- Terada, S., Enomoto, Y., Hanawa, D., and Oguchi, K. Performance of gait authentication using an acceleration sensor. In 2011 34th International Conference on Telecommunications and Signal Processing (TSP) (Aug 2011), pp. 34--36.Google ScholarCross Ref
- Zhang, Y., Pan, G., Jia, K., Lu, M., Wang, Y., and Wu, Z. Accelerometer-based gait recognition by sparse representation of signature points with clusters. IEEE Transactions on Cybernetics 45, 9 (Sep. 2015), 1864--1875.Google Scholar
- Zhao, Y., Qiu, Z., Yang, Y., Li, W., and Fan, M. An empirical study of touchbased authentication methods on smartwatches. In Proceedings of the 2017 ACM International Symposium on Wearable Computers (New York, NY, USA, 2017), ISWC '17, ACM, pp. 122--125. Google ScholarDigital Library
Index Terms
- Walk to Show Your Identity: Gait-based Seamless User Authentication Framework Using Deep Neural Network
Recommendations
A dynamic identity-based user authentication scheme for remote login systems
With the purpose of accessing numerous network resources and services with user anonymity, various dynamic identity ID-based user authentication schemes have been proposed. Recently, Khan et al. have pointed out the security weaknesses of the dynamic ID-...
Identity-Based signcryption from identity-based cryptography
WISA'11: Proceedings of the 12th international conference on Information Security ApplicationsA signcryption scheme encrypts and signs data in a single operation which is more efficient than using an encryption scheme combined with a signature scheme. Identity-based cryptography (IBC) does not require users to pre-compute key pairs and obtain ...
Remarks on fingerprint-based remote user authentication scheme using smart cards
In 2002, Lee, Ryu, and Yoo proposed a fingerprint-based remote user authentication scheme using smart cards. The scheme makes it possible for authenticating the legitimacy of each login user without any password table. In addition, the authors claimed ...
Comments