DATE: Thursday, February 21, 2002
TIME: Noon - 1 pm
PLACE: Hamerschlag Hall, Room 1112

Fabian Monrose

Secure Systems Group
Bell Labs, Lucent Technologies

Cryptographic Key Generation Using Features in a Speaker's Voice

In this talk we propose a technique to reliably generate a cryptographic key from a user's voice while speaking a pass-phrase. Rather than deriving the cryptographic key from merely the password that was spoken---which would constitute little more than an exercise in automatic speech recognition---we strive to generate a substantially stronger cryptographic key with entropy drawn from both the spoken password and how the user speaks it. Moreover, the cryptographic key is designed to resists cryptanalysis even against an attacker who captures and reverse-engineers the device on which the key is generated. Furthermore, we show that the technique is sufficiently robust to enable the user to reliably regenerate the key by uttering her pass-phrase again, and describe an empirical evaluation. In addition, we discuss the major hurdles of implementing our techniques on an off-the-shelf PDA with a 206 Mhz StrongArm processor, a decent audio codec, and an inexpensive microphone. This is joint work with M. K. Reiter (CMU) and Q. Li (Bell Labs).

Fabian received his Ph.D from Courant Institute of Mathematical Science, New York University, in 1999. Since then he joined the Secure Systems Group at Bell Labs, Lucent Technologies. Fabian's research interests are in the areas of network security, user authentication, electronic commerce and biometrics. He is also interested in network operating systems and Internet platforms for supporting next-generation computing.

For Further Seminar Info: