Are fingerprints unique? Not really, AI-based study finds

Published this week in the journal Science Advances, the paper seemingly upends a long-accepted truth about fingerprints: They are not, Guo and his colleagues argue, all unique.

“Do you think that every fingerprint is actually unique?”

It’s a question that a professor asked Gabe Guo during a casual chat while he was stuck at home during the Covid-19 lockdowns, waiting to start his freshman year at Columbia University. “Little did I know that conversation would set the stage for the focus of my life for the next three years,” Guo said.

Guo, now an undergraduate senior in Columbia’s department of computer science, led a team that did a study on the subject, with the professor, Wenyao Xu of the University of Buffalo, as one of his coauthors. Published this week in the journal Science Advances, the paper seemingly upends a long-accepted truth about fingerprints: They are not, Guo and his colleagues argue, all unique.

In fact, journals rejected the work multiple times before the team appealed and eventually got it accepted at Science Advances. “There was a lot of pushback from the forensics community initially,” recalled Guo, who had no background in forensics before the study.

“For the first iteration or two of our paper, they said it’s a well-known fact that no two fingerprints are alike. I guess that really helped to improve our study, because we just kept putting more data into it, (increasing accuracy) until eventually the evidence was incontrovertible,” he said.

To get to its surprising results, the team employed an artificial intelligence model called a deep contrastive network, which is commonly used for tasks such as facial recognition. The researchers added their own twist to it and then fed it a US government database of 60,000 fingerprints in pairs that sometimes belonged to the same person (but from different fingers) and sometimes belonged to different people.

As it worked, the AI-based system found that fingerprints from different fingers of the same person shared strong similarities and was therefore able to tell when the fingerprints belonged to the same individual and when they didn’t, with an accuracy for a single pair peaking at 77% — seemingly disproving that each fingerprint is “unique.”