Privacy-preserving and tokenless chaotic revocable face authentication scheme

With the large-scale proliferation of biometric systems, privacy and irrevocability issues of their data have become a hot research issue. Recently, some researchers proposed a couple of schemes to generate BioHash, e.g. PalmHash, however, in this paper, we point out that the previous schemes are costly in terms of computational complexity and possession of USB tokens to generate pseudorandom numbers. To overcome the problems, we propose a novel chaotic FaceHashing scheme which preserves privacy of a biometric user. The presented scheme does not need users to posses USB tokens in generating pseudorandom sequences, which is a cost-effective solution. Besides, our scheme minimizes the system complexity with simple operations to attain the FaceHash. Experimental results show that the proposed scheme is efficient, secure, and revocable in case FaceHash is theft or compromised.