If you follow what we do at Acrylic Robotics, you know we’re building tech that artists can use to reproduce precise copies of their works at scale, using real paint on canvas. What you might not know is that our robots are now also being tapped to identify art forgeries and prevent fraud.
In early July 2025, Norval Morrisseau—widely regarded as the grandfather of contemporary Indigenous art in Canada—made headlines when a dealer involved in distributing counterfeits of his artwork pleaded guilty. The Morrisseau fraud case is complex, wide-reaching, and dates back decades, with eight individuals arrested in 2023. Organized forgery rings produced thousands of fake replicas of Morrisseau paintings, ultimately inflicting losses of up to CAD$100 million on his estate.
The major perpetrators have received prison sentences, but as far as the estate is concerned, the fight isn’t over—and this week, it announced plans to bring AI into the ring.
The estate is partnering with Acrylic to train an AI model to detect Morrisseau forgeries and restore his legacy and the value of the estate.
Morrisseau died in 2007 amid a widening circle of controversy over fakes and forgeries. Eventually, his estate began assembling an extensive catalogue of his works upon which to train an AI model. Acrylic is supporting this work by having its robots reproduce Morrisseau pieces for the model—called Norval AI—to use as training data.
By analyzing unique characteristics like stroke length, pressure, speed and more, our robots can create highly accurate reproductions of artworks. To detect forgeries, Norval AI compares our reproductions of Morrisseau’s work to authentic pieces verified by the estate. The AI can identify discrepancies in brushstroke patterns and techniques and find deviations that indicate forgery.
It may seem ironic that a key plank in the plan to address forgery is the deliberate production of, well, forgeries. But the robot-made pieces have been requisitioned by the estate—and if all goes well, the project could provide an authoritative way to distinguish impostor pieces from real ones.
The biggest art fraud case in Canada's history
It’s believed that the Morrisseau forgeries began circulating as long ago as the 1990s. Some were sold to auctioneers and galleries which, in turn, sold them to members of the public. The works commanded steep prices. Paintings by Morrisseau have sold for tens of thousands of dollars, with some going for several hundred thousand.
In fact, one such individual buyer was musician Kevin Hearn of Barenaked Ladies fame. According to a 2024 article published by The Walrus, Hearn purchased a work titled Spirit Energy of Mother Earth in 2005. In 2010, he learned it might be fake, and went back to the gallerist who'd sold it to him—but the gallerist would neither consider the idea nor give him any money back.
People like Hearn who unknowingly purchased forgeries have run into substantial legal obstacles trying to prove their Morrisseau paintings were inauthentic. In fact, publicly saying that a work of art is fake can get you sued for art defamation. Word that galleries have sold counterfeit artworks (even unknowingly) is obviously not good for galleries, which tend to push back.
Cory Dingle, manager of the Morrisseau estate, says he and other Indigenous experts who are closely familiar with a painter and their work can determine through visual inspection whether a given piece is genuine—but their word alone is not enough for a buyer that has invested thousands. In fact, earlier this year, Dingle and the Morrisseau estate were sued for $1.45 million by an art gallery for defamation and breach of contract after Dingle spoke out about art fraud to various media outlets.
While currently available authentication methods, such as XRF scanning, can support experts’ assessments of paintings, the traditional art world is not going to just accept the Morrisseau estate’s word on this, says Dingle.
Why provenance matter—and how tech can help
Provenance refers to the documented history of an artwork’s ownership—essentially, a paper trail that traces where the work has been, who has owned it, and how it has changed hands. Provenance helps confirm authenticity, establish value, and protect against theft or fraud. For European or traditional western art, provenance is often recorded in sales records, museum and gallery catalogues, private collection inventories, letters or diaries, exhibition histories and more.
But for Indigenous artworks, provenance may rely more on oral histories. Some Indigenous works of art have been subject to mislabelling (catalogued with little understanding of their cultural origin or meaning) or colonial disruption (being taken, sold or traded without consent or documentation). In addition, many Indigenous artists have operated outside traditional gallery systems.
Not only do these gaps make Indigenous artworks more vulnerable to forgery in the first place—as seen in the Morrisseau case—but they also make it harder to rely on provenance to prove whether a piece is genuine or counterfeit. This frustrates those who know Indigenous art well enough to discern the difference. Just as many western scientists dismiss Indigenous ways of knowing, western art experts tend to distrust art knowledge they don’t understand, preferring their traditional, paper-based approach to tracing provenance.
“However,” says Chloë Ryan, Acrylic Robotics’ co-founder and CEO, “they may trust an objective, third-party AI model that has proven again and again that it can reliably confirm whether art is fake or real. We think AI could be a valuable tool to help establish the authenticity of Indigenous works—or any works, really.”
Designing art to be fraud-proof
A logical next step is to ensure there will be no more forgeries in the future, and Acrylic Robotics is already planning a solution for that. Our idea draws on XRF (X-ray fluorescence) scanning, which can detect carbon materials—found in pencil, ink or graphite, but not paint—hiding beneath paint layers. Copycats often sketch out a painting before copying it, something Morrisseau apparently never did.
Police forces and galleries already use XRF scanners to assess whether paintings are authentic, so the technology isn’t new. But Ryan’s thought is to turn the idea on its head and have our robots use graphite materials on purpose: to sketch out an undisclosed form beneath the first layer of paint on a robotic reproduction that would identify it as an authorized Acrylic Robotics piece. For example, the invisible sketch could be of a robot and specify the artwork’s number in a series.
“So if someone tried to pass off our version as an original, the prospective buyer could run it through a scanner and they would notice the Acrylic underwriting. As one in a limited series of robot-produced pieces, it would still have value—but it would be impossible to pass it off as original,” says Ryan. “It’s extremely important to us that our reproductions don’t contribute to forgery problems.”
XRF scanners are costly, so this solution is accessible to galleries, not individuals. But Ryan has a solution for retail buyers, too: NFC tags (small, programmable stickers) added to Acrylic Robotics’ paintings before the first layer of paint goes on.
“As the owner, you could tap your phone over the corner of the painting, and it would pop to our website and show you information about the edition and the artist, possibly even with a video of the painting being made by our robot.”
These and other authentication approaches—such as signed certificates of authenticity—are still ideas in development here. To Ryan, what’s most exciting is the enormous potential she sees in the technology.
“Hopefully we can be a little useful in helping to train Norval AI to detect fraud,” she says. “But this is really just the tip of the iceberg for the art world.”
