Fingerprints are no longer a trustworthy means of identification. Fingerprint authentication systems are widely trusted, and used on billions of smartphones, worldwide. But a new study from New York University Tandon School of Engineering shows a surprising level of vulnerability in these systems. In a process called MasterPrints, a neural network can be trained to synthesize human fingerprints, and a research team has developed a fake fingerprint capable of fooling a touch-based authentication system.

This development is built on earlier research done by Nasir Memon, a professor of computer science and engineering at NYU Tandon. Memon coined the term “MasterPrint,” and described how fingerprint systems use a partial fingerprint, instead of a full one, to confirm identity. Partial fingerprints are not likely to be as unique as a full print.

Philip Bontrager, the lead author of the paper presented at the IEEE International Conference of Biometrics. Bontrager and his colleagues trained a Machine Learning algorithm to produce synthetic fingerprints as “MasterPrints.” They created complete images of artificial fingerprints, Bontrager said, “Fingerprint-based authentication is still a strong way to protect a device or a system, but at this point, most systems don’t verify whether a fingerprint or other biometric is coming from a real person or a replica. These experiments demonstrate the need for multi-factor authentication, and should be a wake-up call for device manufacturers about the potential for artificial fingerprint attacks.”

Read more at PR Newswire.