AI/MLNews

Artificial fingerprints could hack into one in three smartphones

0

Did you know your smartphone captures just a partial fingerprint of yours and not the one in its entirety to verify your identity to access your device? The obvious reason is the lack of required space on your device. Taking cue from this, researchers at New York University and Michigan State University have developed a set of artificial fingerprints, called DeepMasterPrints for unlocking fingerprint-protected devices.

“Since small portions of a fingerprint are not as distinctive as the full fingerprint, the chances of a partial fingerprint (from one finger) being incorrectly matched with another partial fingerprint (from a different finger) are higher,” the researchers said in their paper.

According to a CNBC report, DeepMasterPrints act as a kind of “masterkey” which have the potential to hack into one in three fingerprint sensor-enabled smartphones.

Your device has sets of your partial fingerprints. “If you store images for three of your fingers the device may keep around 30 partial fingerprints,” the researchers were quoted as saying. “With MasterPrints you just have to create a few — five or ten and I’m in business.”

This could be a way to unlock a “reasonably large” number of phones — just under a third. “If every fifth phone works it would be a profitable scam,” they said.

Probing around the vulnerability to MasterPrints is critical for researchers designing secure systems as “it allows them to evaluate the immediate risk of this threat, and it gives them a concrete attack vector to protect against,” the paper said.

The researchers that are part of the study are Philip Bontrager, Aditi Roy, Julian Togelius, Nasir Memon, and Arun Ross.

Get latest updates in your inbox, subscibe to our daily newsletter.