Robust anti-fraud algorithms against malicious AI-generated face images and travel documents

• Unité de recherche: INNOSUISSE
• Numéro de projet: 106.729 IP-ICT
• Titre du projet anglais: Robust anti-fraud algorithms against malicious AI-generated face images and travel documents

Mots-clé (Anglais)

ICT, Deep learning

Résumé des résultats (Abstract) (Anglais)

The project aim is twofold: i) develop robust defenses against deepfakes both for identity document images and selfie-videos, and ii) take advantage of the capabilities of generative AI to improve the state of the art in digital authentication by making algorithms more robust and balanced.