Paris, June 17, 2026
Facial recognition and analysis are rapidly becoming widespread in many aspects of daily life: smartphone authentication, remote bank account opening, border control, and access to public and private services. This generalization is accompanied by high expectations regarding security, fluidity, and reliability, but also by growing concerns about the robustness and fairness of these systems.
These types of issues, which highlight the biases that can affect current AI models, are at the core of the work carried out by the the Artefact Research Center, which collaborates with university professors to develop more transparent and ethical models. Indeed, while current AI models are accurate and easy to implement in many use cases, they often remain unmanageable due to their opaque nature, raising numerous ethical concerns.
As part of the doctoral research program “Fairness in Computer Vision,” the Artefact Research Center has developed a unique methodology for identifying, analyzing, and correcting biases in 3D facial reconstruction models based on selfies, and has, for the first time, highlighted biases related to age and, to a lesser extent, to individuals’ ethnic backgrounds.
Given the complexity and scarcity of reference 3D data, a methodology based on facial curvature analysis was developed. This approach enables accurate detection of poorly reconstructed areas, even with a limited number of high-precision scans, and is highly aligned with human perception of distortions, based on our experiments. Furthermore, the areas colored by the level of bias are easy to visualize and interpret, enhancing the transparency of the methodology. This work was submitted to the peer-reviewed scientific conference ECCV, the European Conference on Computer Vision.
To illustrate this work, the experience at the Artefact booth will allow visitors to generate a 3D model of their face using a smartphone, and then compare it to a high-definition scan taken on-site. The algorithm will highlight any observed discrepancies and potential disparities, and compare them with the visitor’s perception of poorly reconstructed areas of their face. Various visualizations of the methodology will be displayed, illustrating its ability to improve the performance and fairness of the models.
Open to all visitors throughout the duration of the exhibition, “Beyond the Mask” showcases Artefact’s commitment to responsible artificial intelligence, combining technological excellence, scientific rigor, and societal impact.
Vincent Luciani, co-founder and CEO of Artefact, says: “Artefact’s DNA is all about transforming breakthroughs from basic research into concrete solutions that can be directly deployed by our clients. With Beyond the Mask, we are at the heart of this effort. We are working to better understand the limitations—particularly regarding bias—of computer vision technologies already widely deployed in authentication applications, in order to correct them in a practical way. The challenge is not merely technological: it is about making these systems more reliable under real-world conditions.”
About Artefact
Artefact is an international data and AI consulting firm headquartered in Paris. For the past 10 years, the company has specialized in the design and deployment of artificial intelligence technologies and data-driven solutions, with a mission to accelerate the adoption of AI to create a positive impact on individuals and organizations.
As a pioneer in its field, leveraging data and advanced artificial intelligence technologies, our teams of business consultants and engineers work together to develop solutions that drive business impact and improve productivity across the entire corporate value chain, while ensuring the ethical and responsible use of data.
Combining cutting-edge technological expertise with operational excellence, Artefact supports more than 1,000 companies worldwide in accelerating their business transformation, including over 300 international firms. Its 2,500 experts, based in 36 offices around the globe, serve all key sectors of the economy: manufacturing, retail, luxury goods, mass consumption, healthcare, finance, and more.
Press Contact: nicolas.fossiez@taddeo.fr
