When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection

no code implementations • 7 Aug 2023 • Mohammed Lansari, Reda Bellafqira, Katarzyna Kapusta, Vincent Thouvenot, Olivier Bettan, Gouenou Coatrieux

Most existing works have focused on watermarking in a centralized manner, but only a few methods have been designed for FL and its unique constraints.

Federated Learning Privacy Preserving

White-box Membership Attack Against Machine Learning Based Retinopathy Classification

no code implementations • 30 May 2022 • Mounia Hamidouche, Reda Bellafqira, Gwenolé Quellec, Gouenou Coatrieux

From a privacy perspective in our use case where a diabetic retinopathy classification model is given to partners that have at their disposal images along with patients' identifiers, inferring the membership status of a data sample can help to state if a patient has contributed or not to the training of the model.

BIG-bench Machine Learning Inference Attack +2