Voice Passwords Revisited

Chenguang Yang, Ghaith Hammouri, Berk Sunar

2012

Abstract

We demonstrate an attack on basic voice authentication technologies. Specifically, we show how one member of a voice database can manipulate his voice in order to gain access to resources by impersonating another member in the same database. The attack targets a voice authentication system build around parallel and independent speech recognition and speaker verification modules and assumes that adapted Gaussian Mixture Model (GMM) is used to model basic Mel-frequency cepstral coefficients (MFCC) features of speakers. We experimentally verify our attack using the YOHO database. The experiments conclude that in a database of 138 users an attacker can impersonate anyone in the database with a 98% success probability after at most nine authorization attempts. The attack still succeeds, albeit at lower success rates, if fewer attempts are permitted. The attack is quite practical and highlights the limited amount of entropy that can be extracted from the human voice when using MFCC features.

Download


Paper Citation


in Harvard Style

Yang C., Hammouri G. and Sunar B. (2012). Voice Passwords Revisited . In Proceedings of the International Conference on Security and Cryptography - Volume 1: SECRYPT, (ICETE 2012) ISBN 978-989-8565-24-2, pages 163-171. DOI: 10.5220/0004060201630171

in Bibtex Style

@conference{secrypt12,
author={Chenguang Yang and Ghaith Hammouri and Berk Sunar},
title={Voice Passwords Revisited},
booktitle={Proceedings of the International Conference on Security and Cryptography - Volume 1: SECRYPT, (ICETE 2012)},
year={2012},
pages={163-171},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004060201630171},
isbn={978-989-8565-24-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Security and Cryptography - Volume 1: SECRYPT, (ICETE 2012)
TI - Voice Passwords Revisited
SN - 978-989-8565-24-2
AU - Yang C.
AU - Hammouri G.
AU - Sunar B.
PY - 2012
SP - 163
EP - 171
DO - 10.5220/0004060201630171