Researchers Trick Phone's Fingerprint Reader With AI-Generated 'MasterPrints'

Get ready to see this little piece of tech in the next Mission Impossible movie: AI-generated thumb prints capable of fooling a smart phone’s fingerprint scanner. A group of researchers from New York University have created so-called “MasterPrints” that act as a skeleton key for about 20% of the population, thanks to the fact that most phones only use partial prints in their security system.

Though your thumbprint is technically unique to you, most smart phones don’t store or check the entire print when they verify your thumb. Instead, only parts of your thumb are used, and some of those parts are identical to other people’s thumbs. By trawling databases of partial prints and compositing them together, researchers were able to create the first ‘MasterPrint.’ The team then took things a step further by enlisting an AI to help refine the process, allowing them to create synthetic MasterPrints that could match one in five people’s partial thumbprints.

According to Philip Bontrager, who is involved with the project: “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.”

AI-driven biometrics have been finding more and more use recently, with lie-detecting kiosks being tested in EU airports and new gait recognition technology being integrated into the Chinese surveillance industry, to name just a few instances. With the help of number-crunching artificial intelligence tools, more data can be analyzed and organized more easily than ever before. Speaking of which, gait recognition was used in a recent Mission Impossible movie.