DeepMasterPrint: Fingerprint Spoofing via Latent Variable Evolution

Biometric authentication is important for a large range of systems, including but not limited to consumer electronic devices such as phones. Understanding the limits of and attacks on such systems is therefore crucial. This paper presents an attack on fingerprint recognition system using MasterPrints, synthetic fingerprints that are capable of spoofing multiple people’s fingerprints. The method described is the first to generate complete image-level Masterprints, and further exceeds the attack accuracy of previous methods that could not produce complete images. The method, Latent Variable Evolution, is based on training a Generative Adversarial Network on a set of real fingerprint images. Stochastic search in the form of the Covariance Matrix Adaptation Evolution Strategy is then used to search for latent variable (inputs) to the generator network that optimize the number of matches from a fingerprint recognizer. We find MasterPrints that a commercial fingerprint system matches to 23% of all users in a strict security setting, and 77% of all users at a looser security setting. The underlying method is likely to have broad usefulness for security research as well as in aesthetic domains.