protection

The Shield

At Inria Startup Studio, I lead research on protecting faces, voices and creative work against unauthorised use for AI model training and generation.

The current project, Beepfake, is a protection for images and voices against non-consensual AI cloning, and a benchmark of such protections, with Inria and the National University of Singapore. I study adversarial machine learning: how robust such protections stay against adaptive attacks.

The Conversation, 2026 (in French)

Try to copy this face. Then protect it, and try again.