The Role of AI in Dismantling International Art Forgery Rings

Art Forgery at the Louvre Museum. Photo by cangaroojack via Flickr

An art forgery ring was recently uncovered by authorities in Italy. This comes just months after authorities in Pisa discovered a string of European workshops. The growing issue of selling fake artwork is largely being combated by new AI technology. 

In late February, the Carabinieri’s Cultural Heritage Protection Unit uncovered the operation in Rome. Italian forces traced the paintings to online postings on auction sites such as eBay and Catawiki. This collection included fake works from world-renowned artists such as Pablo Picasso, Andy Warhol, Rembrandt van Rijn and Dora Maar.

Upon raiding the site, the Carabinieri found an array of art supplies, including different kinds of paint, canvases, brushes, easels and stencils. They also found falsified artist signatures, gallery stamps and certificates of authenticity.

71 falsified paintings were discovered. While no arrests have been confirmed, a prominent art restorer has been identified as a suspect. 

This bust came soon after Italian authorities exposed an international forgery plot, uncovering 2,100 fake artworks attributed to more than 30 artists, primarily Banksy. These forgery workshops were located in Italy, Spain and Belgium. Italian police were initially notified of these crimes in 2023 after they recovered 200 forgeries from a collection in Pisa.

So far, 38 people have been placed under investigation and charged with conspiracy to handle foreign goods, forgery and illegal sale of artwork. The value of the forgeries, if sold at market value for the originals, was estimated at $213 million/€200 million.

As authorities crack down on physical forgery networks, AI technology is proving to be a critical tool in detecting counterfeit art sold online. Since May 2024, Dr. Carina Popovici, the head of Art Recognition and a specialist in art authentication, has been using AI to detect forgeries in online postings. Popovici’s team estimates a 95% accuracy rate in identifying forged artworks. 

This technology analyzes minute details in the auctioned paintings, focusing on details such as brush strokes and paint colors. Popovici said, “In the past, it was really difficult to spot these things because you can’t take samples from an image on the internet. But, with the new technology, it’s easy. You can just download an image, and then in ten minutes, you will know. I think that people should be warned.”

The incorporation of AI into this process has increased productivity and accuracy, according to Popovici. “You would have to pack your painting, ship it off to a different country for appraisal…Then you would have to wait for some months, or sometimes even years, for an answer,” she said. “Our program needs about three days to learn the characteristics from around 700 training images, and less than five minutes to calculate the probability of the authenticity of an artwork.”

Art Recognition is not the only company leveraging AI in this process. Hephaestus Analytical focuses on the largely corrupt Russian market in which 95% of the paintings analyzed by this team are fake. Founder Denis Mosieev said, “The market is so saturated with forgeries that it’s impossible not to talk about it. We believe our technology can clean up the market. It is a solvable problem.”

Nicholas Eastaugh, CEO of the authentication firm Varsarik, emphasized that AI should not replace human judgment but rather serve as a tool for experts.