Paper accepted to IJCB 2025

Our paper entitled “VOIDFace: Towards an Effective Face Training Data Storage and Protection with Right to be Forgotten Property“, has been accepted for presentation at IJCB 2025 that will be held in Osaka, Japan on September 8-11 2025!

This year, IJCB 2025, a flagship conference from IEEE Biometrics Council, was highly competitive, with only 95 papers accepted out of 243 submissions—an acceptance rate of 39.1%. A big congrats towards Ajnas Muhammed. ?

This research marks an important step toward secure and privacy-aware face recognition systems, ensuring performance and compliance with the Right to be Forgotten. For the best of our knowledge, this is the first work to ensure security and privacy in the sense of the Right To Be Forgotten. The main idea is to split enrollment portraits into Visual Secret Shares and keep one of them for a Trusted Third Party (guaranteeing that the portrait will never be reconstructed again after an authorization withdrawal from the citizen) while creating a training DL architecture able to achieve state of the art performance in a distributed learning architecture.

This project received funding from the European Union’s Horizon Europe research and innovation programme under Grant Agreement No 101189689 and from national funds through FCT- Fundacão para a Ciência e a Tecnologia, under the project UID/00048.