The research suggests that fingerprints may not be as unique as previously believed. By using an AI model trained on a database of 60,000 fingerprints, the researchers found that the AI was able to identify whether prints from different types of fingers came from the same person with 75 to 90 percent accuracy, using angles and curvatures of the swirls at the center, rather than the traditional minutiae. The claims have faced pushback from forensic scientists, with one professor arguing that the findings are not necessarily new and do not disprove current forensic techniques.