Carnegie Mellon University School of Computer Science Technical Report CMU-CS-00-134, May 2000.
Andrew J. Klosterman and Gregory R. Ganger
Dept. of Electrical and Computer Engineering
Carnegie Mellon University
Pittsburgh, PA 15213
http://www.pdl.cmu.edu/
Biometrics have the potential to solidify person-authentication by examining
"unforgeable" features of individuals. This paper explores issues involved
with effective integration of biometric-enhanced authentication into
computer systems and design options for addressing them. Because biometrics
are not secrets, systems must not use them like passwords; otherwise,
biometric-based authentication will reduce security rather than increase
it. A novel biometric-enhanced authentication system, based on a trusted
camera that continuously uses face recognition to verify identity, is
described and evaluated in the context of Linux. With cryptographically-signed
messages and continuous authentication, the difficulty of bypassing
desktop authentication can be significantly increased.
FULL PAPER: pdf / postscript