PXL Vision to collaborate with Idiap for research project to fight deepfakes

Swiss digital identity provider PXL Vision is collaborating with the Idiap Research Institute in a project to develop deepfake detection. If successful, the project will bring the first robust algorithm for deep facial recognition to the market. The project leverages synthetic data to improve accuracy across all populations.

The Swiss innovation agency Innosuisse has awarded a contract for the 18-month project to Idiap as a research partner and PXL Vision as an implementation partner.

The project will “cover the entire global population with a new synthetic and balanced dataset of faces (in terms of gender, age, skin color)” to improve accuracy and mitigate bias in future PXL Vision products, says Michael Born, CEO of PXL Vision.

“We are looking forward to working with the identity verification expert PXL Vision and researching this important and future-oriented topic,” says Sebastien Marcel, head of biometrics security and privacy, as well as AI for trust at Idiap.

Idiap recently got involved with a collaboration to fight generative AI spoofing that could circumvent age verification.

Article Topics

biometric liveness detection  |  deepfake detection  |  deepfakes  |  facial recognition  |  Idiap  |  PXL Vision