With the proliferation of biometric scanning, some hidden risks
Features the research of Nasir Memon, and Julian Togelius, professors in the Department of Computer Science and Engineering at NYU Tandon.
… A team of researchers at New York University’s Tandon School of Engineering, for instance, created an algorithm to not only simulate a person’s fingerprint but to create a single print that can masquerade as several others and fool scanners as often as 20 percent of the time — all without replicating an actual print. ... Much like a master key can fit many different locks, the NYU Tandon [School of Engineering] algorithm, called DeepMasterPrints, focuses on generating artificial prints that contain enough common fingerprint characteristics to allow them to fool fingerprint sensors into believing they’re a match. In order to do this, researchers use a three-step process.
