Scientists Proved With A Help Of AI That Fingerprints Are Not Really Unique

Artificial intelligence appears to have helped revolutionize forensic science. It turned out that our knowledge about the uniqueness of fingerprints was false. Everyone knows that every person has unique fingerprints. A lesser-known fact, but nevertheless very important for forensic science, is that each finger of each person also has a unique fingerprint. More precisely, everyone thought so until now. It turned out that this is not entirely true.

Artificial intelligence appears to have helped revolutionize forensic science. It turned out that our knowledge about the uniqueness of fingerprints was false.

Everyone knows that every person has unique fingerprints. A lesser-known fact, but nevertheless very important for forensic science, is that each finger of each person also has a unique fingerprint. More precisely, everyone thought so until now. It turned out that this is not entirely true.

Scientists using artificial intelligence (AI) have made a discovery that could revolutionize the world of forensics. According to the Daily Mail, researchers from Columbia University have discovered that prints from different fingers on the same hand can actually be linked.

The idea to turn to artificial intelligence for help came to master’s student in engineering Gabe Guo, who had no previous experience in forensic science. He decided to feed the AI ​​about 60 thousand fingerprints and ask him to find similarities in them: most of the fingerprints belonged to different people, but some of them were taken from two different fingers of the same person.

Over time, AI was able to detect fingerprints belonging to the same people, despite the fact that they looked completely different – something previously thought impossible. It is noted that the AI ​​was thus able to compare even fingerprints from different fingers of different hands of the same person.

The scientific article was published yesterday in the journal Science, but in fact the path to publication was not easy for the authors.  When the team received the results, they submitted them to a well-known crime journal, but were rejected a few months later.  Moreover, with the wording in the form “it is well known that each fingerprint is unique,” ​​and therefore it is impossible to detect similarities, even if the fingerprints belong to the same person.

The study authors said they were aware of the potential bias in the data. However, in their opinion, artificial intelligence works the same regardless of gender and race.

However, Guo said he was confident the discovery could improve criminal investigations.

Natalia Ganeva

Natalia Ganeva

Natalia Ganeva is a young and enthusiastic technology journalist who brings a fresh perspective to the tech reporting landscape. Natalia's articles and features showcase her dedication to staying abreast of the latest tech trends and her ability to convey complex topics in an accessible manner.