Abstract—In this paper, we present an iris-based access control protocol that is resistant to iris-based replay attacks. This new style of biometric-based access control protocol is similar to the so called, ‘one time password’ approach used by some conventional username/password access protocols. Our results show that not only is this new type of iris-based access protocol effective, it can also distinguish between when a user attempting to gain access has supplied a poor sample of their iris and when the access control system is experiencing an iris-based replay attack.
Index Terms—Biometrics, cyber security, genetic and evolutionary computation, iris recognition.
Joseph Shelton, Kaushik Roy, Brian O’Connor, and Gerry V. Dozier are with the Computer Science Department, North Carolina Agricultural and Technical State University, Greensboro, NC 27405 USA (e-mail: jashelt1@ aggies.ncat.edu, kroy@ncat.edu, bpoconno@aggies.ncat.edu, gvdozier@ncat.edu).
Cite: Joseph Shelton, Kaushik Roy, Brian O’Connor, and Gerry V. Dozier, "Mitigating Iris-Based Replay Attacks," International Journal of Machine Learning and Computing vol.4, no. 3, pp. 204-209, 2014.