PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
机构 * University of Connecticut(康涅狄格大学) ; Iowa State University(爱荷华州立大学) ; The University of Kansas(堪萨斯大学) ; University of Illinois at Chicago(伊利诺伊大学香槟分校) ; Cisco Research(思科研究)
Comments Source code is available at https://github.com/datasec-lab/plrvo. This is the full version of the paper to appear in CCS'25