Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD

1 July 2023

Papers citing "Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD"

5 / 5 papers shown

Title
Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy Jamie Hayes Ilia Shumailov Eleni Triantafillou Amr Khalifa Nicolas Papernot MU 25 25 0 02 Mar 2024
Individual Privacy Accounting with Gaussian Differential Privacy A. Koskela Marlon Tobaben Antti Honkela 27 18 0 30 Sep 2022
Bounding Training Data Reconstruction in Private (Deep) Learning Chuan Guo Brian Karrer Kamalika Chaudhuri L. V. D. van der Maaten 97 47 0 28 Jan 2022
Manipulating SGD with Data Ordering Attacks Ilia Shumailov Zakhar Shumaylov Dmitry Kazhdan Yiren Zhao Nicolas Papernot Murat A. Erdogdu Ross J. Anderson AAML 109 87 0 19 Apr 2021
Individual Privacy Accounting via a Renyi Filter Vitaly Feldman Tijana Zrnic 46 77 0 25 Aug 2020