Robust or Private? Adversarial Training Makes Models More Vulnerable to Privacy Attacks

15 June 2019

Papers citing "Robust or Private? Adversarial Training Makes Models More Vulnerable to Privacy Attacks"

5 / 5 papers shown

Title
Reconstructing Training Data from Trained Neural Networks Niv Haim Gal Vardi Gilad Yehudai Ohad Shamir Michal Irani 40 132 0 15 Jun 2022
Privacy Leakage of Adversarial Training Models in Federated Learning Systems Jingyang Zhang Yiran Chen Hai Helen Li FedML PICV 27 15 0 21 Feb 2022
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations Amin Ghiasi Hamid Kazemi Steven Reich Chen Zhu Micah Goldblum Tom Goldstein 34 15 0 31 Jan 2022
On the human-recognizability phenomenon of adversarially trained deep image classifiers Jonathan W. Helland Nathan M. VanHoudnos AAML 22 4 0 18 Dec 2020
Conditional Image Synthesis With Auxiliary Classifier GANs Augustus Odena C. Olah Jonathon Shlens GAN 229 3,190 0 30 Oct 2016