Synthetic fingerprints can fool sensors
Article features research by a team including Philip Bontrager, a Ph.D. student at the NYU Game Innovation Lab at NYU Tandon, and lab director Julian Togelius and Nasir Memon, both professors in the Department of Computer Science and Engineering, and Aditi Roy, post-doc researcher in the department.
Researchers at the New York University Tandon School of Engineering (Brooklyn, NY) have created synthetic fingerprints that are capable of spoofing smartphone fingerprint sensors.
The researchers used a neural network trained to synthesize human fingerprints to create a fake fingerprint that could potentially fool a touch-based authentication system for up to one in five people. Such a "DeepMasterPrint" - similar to a master key that can unlock every door in a building - uses artificial intelligence (AI) to match a large number of prints stored in fingerprint databases and can thus theoretically unlock a large number of devices.
