Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
机构 * Department of CISE, University of Florida, USA.(佛罗里达大学计算机与信息科学系) ; Center for Nonlinear Studies, Los Alamos National Lab, USA(洛斯阿拉莫斯国家实验室非线性研究中心) ; Computational Science Center, National Renewable Energy Laboratory, USA(国家可再生能源实验室计算科学中心)
Comments Accepted to ICML 2025