R-CONV: An Analytical Approach for Efficient Data Reconstruction via
Convolutional Gradients

R-CONV: An Analytical Approach for Efficient Data Reconstruction via Convolutional Gradients

6 June 2024

Alessandro Savino

Adnan Qayyum

Papers citing "R-CONV: An Analytical Approach for Efficient Data Reconstruction via Convolutional Gradients"

6 / 6 papers shown

Title
Understanding Training-Data Leakage from Gradients in Neural Networks for Image Classification Cangxiong Chen Neill D. F. Campbell FedML 44 24 0 19 Nov 2021
R-GAP: Recursive Gradient Attack on Privacy Junyi Zhu Matthew Blaschko FedML 54 136 0 15 Oct 2020
Inverting Gradients -- How easy is it to break privacy in federated learning? Jonas Geiping Hartmut Bauermeister Hannah Dröge Michael Moeller FedML 100 1,223 0 31 Mar 2020
Exploiting Unintended Feature Leakage in Collaborative Learning Luca Melis Congzheng Song Emiliano De Cristofaro Vitaly Shmatikov FedML 142 1,474 0 10 May 2018
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning Briland Hitaj G. Ateniese Fernando Perez-Cruz FedML 115 1,401 0 24 Feb 2017
Communication-Efficient Learning of Deep Networks from Decentralized Data H. B. McMahan Eider Moore Daniel Ramage S. Hampson Blaise Agüera y Arcas FedML 401 17,468 0 17 Feb 2016