Remarks on BioHash and its mathematical foundation

The mathematical foundation of BioHash, a technique used to combine tokenized random number and biometrics, is described. BioHash is an ensemble of random projections to preserve the intra-class variations while enhancing the inter-class variations, and thus it is able to achieve zero error rate when the legitimate token is used or when the biometric data is stolen. Its performance reverts to the original state when the legitimate token is stolen and used by the imposter to claim as the legitimate user. The technique offers two possible error outcomes known as false accept rate (FAR) and false reject rate (FRR). The technique acts as a novel form of biometrics, which can solve the non-revocable and privacy invasion issue of the conventional biometrics. The system has been widely deployed in various security systems due to its immutable characteristics.