Autenticação contínua para smartphones baseada em assinatura acústica
Abstract
With the increasing of data and sensible information stored in smartphones, control the access to this devices is essential in order to mitigate risks. In this sense, a variety of authentication mechanisms has been explored, as the use of passwords and gestures. However, users tend to set weak password combinations or gestures that are easy to reproduce. This fact has been stimulating the research for continuous authentication methods, based on the user's interaction, which also run in background. The purpose of this paper is a new continuous authenticating method based on acoustic signature that is produced by the user-smartphone's interaction.
References
Alkilani, A. and Shirkhodaie, A. (2013). Acoustic signature recognition technique for Human-Object Interactions (HOI) in persistent surveillance systems. Proc. SPIE 8745, Signal Processing, Sensor Fusion, and Target Recognition XXII, May, doi:10.1117/12.2018627.
Serwadda, A. and Phoha, V. V. (2013). When kids toys breach mobile phone security. ACM SIGSAC conference on Computer & communications security (CCS '13).
Govindarajan, S., Gasti, P. and Balagani, K. S. (2013). Secure privacy-preserving protocols for outsourcing continuous authentication of smartphone users with touch data. Biometrics: Theory, Applications and Systems (BTAS), IEEE Sixth International Conference on, vol., no., pp.1-8, doi: 10.1109/BTAS.2013.6712742.
JAudio 1.0 (2013). http://jaudio.sourceforge.net, Acesso em Julho.
Song, Y., Salem, M. B., Hershkop, S. and Stolfo, S. J. (2013). System level user behavior biometrics using fisher features and gaussian mixture models. Security and Privacy Workshops (SPW), 2013 IEEE, pages 52-59, May.
Duda, P. E. H. R. O. and Stork, D. G. (2001). Pattern Classication. Wiley-Interscience Publication.
Liaw, A. and Wiener, M. (2002). Classification and Regression by randomForest. R News, v.2, n.3, December, pp.18-22.
