Do Gradient Inversion Attacks Make Federated Learning Unsafe?

NVIDIA researchers published a study in IEEE Transactions of Medical Imaging investigating whether gradient inversion attacks compromise federated learning safety, finding that such attacks can reconstruct training data from shared gradients, posing privacy risks in medical imaging applications.

Research Labs All Research Labs Spatial Intelligence Applied Research Autonomous Vehicles Deep Imagination Publications AI Playground New and Featured AI Art Gallery NGC Demos Research Areas AI & Machine Learning 3D Deep Learning Computer Vision Robotics All Areas Careers Academic Collaborations Government Collaborations Graduate Fellowship Internships Research Openings Research Scientists Meet the Team Licensing Skip to main content Artificial Intelligence Computing Leadership from NVIDIA Login Research Labs All Research Labs Spatial Intelligence Applied Research Autonomous Vehicles Deep Imagination Publications AI Playground New and Featured AI Art Gallery NGC Demos Research Areas AI & Machine Learning 3D Deep Learning Computer Vision Robotics All Areas Careers Academic Collaborations Government Collaborations Graduate Fellowship Internships Research Openings Research Scientists Meet the Team Licensing Search Search Enter the terms you wish to search for. Publications Do Gradient Inversion Attacks Make Federated Learning Unsafe? Do Gradient Inversion Attacks Make Federated Learning Unsafe? Authors Ali Hatamizadeh Hongxu Danny Yin Pavlo Molchanov Andriy Myronenko Wenqi Li Prerna Dogra NVIDIA Andrew Feng NVIDIA Mona G Flores NVIDIA Jan Kautz Daguang Xu Holger Roth Publication Date Tuesday, January 24, 2023 Published in IEEE Transactions of Medical Imaging Research Area Medical