This new AI model can detect counterfeit Lacoste items from photos

The race to combat counterfeit goods has gained a powerful new ally with the development of an AI image-recognition model capable of identifying fake products from photographs.

Technology breakthrough: Vrai AI, a French company whose name means “true,” has developed an AI system that can detect counterfeit products with 99.7% accuracy by analyzing visual details.

• The system was trained on thousands of images of genuine products to identify subtle discrepancies that may indicate counterfeiting
• The technology can distinguish between normal manufacturing variations and actual counterfeits
• David G. Stork, the company’s chief scientist and Stanford University visiting professor, brings expertise in using AI for art authentication to the project

Initial implementation: Luxury brand Lacoste has become the first corporate customer to deploy this anti-counterfeiting technology.

• The system helps identify fraudulent returns where authentic items are purchased but counterfeit versions are returned
• Warehouse employees can verify product authenticity by taking photos through the Vrai AI app
• The AI analyzes multiple subtle details in Lacoste’s iconic crocodile logo, including eye placement, color shading, and stitch spacing

Market impact: Counterfeit goods represent a significant economic and safety challenge across multiple industries.

• Counterfeit products account for an estimated 2.5% of global commerce
• Companies lose billions of dollars annually to counterfeit goods
• Brand reputation suffers when customers receive fake products, according to fashion consultant Karen Harvey, who notes that consumers typically blame the authentic brands rather than counterfeiters

Future applications: Vrai AI is expanding its focus beyond fashion to address more critical counterfeiting issues.

• The company plans to tackle counterfeit medicines, which the OECD links to hundreds of thousands of deaths annually
• The CDC recently warned about online pharmacies selling millions of counterfeit pills containing fentanyl
• The company is exploring partnerships with major pharmaceutical companies to obtain the approximately 50,000 photos needed to train its algorithm for medicine authentication

Strategic development: The broader context of Vrai AI’s emergence reveals a calculated approach to market entry.

• The technology was developed within Cypheme, which currently sells anti-counterfeiting sticker solutions
• Revenue from Cypheme’s existing business is funding Vrai AI’s development
• The company is in the process of spinning off Vrai AI as a separate entity

Looking ahead: While the technology shows promise in fashion and pharmaceutical applications, its success will largely depend on achieving widespread adoption and maintaining its high accuracy rate across diverse product categories. The challenge of staying ahead of increasingly sophisticated counterfeiters will require continuous innovation and adaptation of the AI model.