LOKI: Large-scale Data Reconstruction Attack Against Federated Learning Through Model Manipulation
45TH IEEE SYMPOSIUM ON SECURITY AND PRIVACY, SP 2024（2024）
Key words
Federated Learning,Reconstruction Attacks,User Data,Data Privacy,Reconstruction Quality,Single Round,Training Round,Weight Gradient,Changes In Parameters,Convolutional Layers,Batch Size,Single Image,Number Of Images,Fundamental Problem,Convolution Kernel,Fully-connected Layer,Scale Of The Problem,Units In Layer,Number Of Kernels,Leakage Rate,Individual Updates,Local Iterations,Magnitude Of Parameters,Differential Privacy,Class Of Attacks,Client Data,Average Pixel Intensity,Threat Model,Learning Rate,Model Parameters
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined