Fetching the paper…
Reading the bibliography…
We explore Reconstruction Robustness (ReRo), which was recently proposed as an upper bound on the success of data reconstruction attacks against machine learning models.
“Membership inference attacks from first principles”
Nicholas Carlini et al · 1914
Earlier work this paper cites.
“On the problem of the most efficient tests of statistical hypotheses”
Jerzy Neyman and Egon Pearson · 1933
Earlier work this paper cites.
“Theoretical statistics”
D.R. Cox and D.V. Hinkley · 1979
Earlier work this paper cites.
“Differential privacy”
Cynthia Dwork · 2006
Earlier work this paper cites.
“A statistical framework for differential privacy”
Larry Wasserman and Shuheng Zhou · 2010
Earlier work this paper cites.
“Deep learning with differential privacy”
Martin Abadi et al · 2016
Earlier work this paper cites.
“Rényi differential privacy”
Ilya Mironov · 2017
Earlier work this paper cites.
“Privacy amplification by subsampling: Tight analyses via couplings and divergences”
Borja Balle, Gilles Barthe and Marco Gaboardi · 2018
Earlier work this paper cites.
“Inverting gradients-how easy is it to break privacy in federated learning?”
Jonas Geiping, Hartmut Bauermeister, Hannah Dröge and Michael Moeller · 2020
Earlier work this paper cites.
“Hypothesis testing interpretations and Rényi Differential Privacy”
Borja Balle et al · 2020
Cited alongside, same era.
“Sharp composition bounds for Gaussian differential privacy via Edgeworth expansion”
Qinqing Zheng, Jinshuo Dong, Qi Long and Weijie Su · 2020
Cited alongside, same era.
“Deep Learning with Gaussian Differential Privacy”
Zhiqi Bu, Jinshuo Dong, Qi Long and Weijie Su · 2020
Cited alongside, same era.
“Gaussian Differential Privacy”
Jinshuo Dong, Aaron Roth and Weijie Su · 2021
Cited alongside, same era.
“Extracting Training Data from Large Language Models.”
Nicholas Carlini et al · 2021
Cited alongside, same era.
“Numerical composition of differential privacy”
Sivakanth Gopi, Yin Lee and Lukas Wutschitz · 2021
Cited alongside, same era.
“Optimal accounting of differential privacy via characteristic function”
Yuqing Zhu, Jinshuo Dong and Yu-Xiang Wang · 2022
Later among the works it cites.
“Connect the dots: Tighter discrete approximations of privacy loss distributions”
Vadym Doroshenko et al · 2022
Later among the works it cites.
“Analytical composition of differential privacy via the edgeworth accountant”
Hua Wang et al · 2022
Later among the works it cites.
“The Saddle-Point Accountant for Differential Privacy”
Wael Alghamdi et al · 2022
Later among the works it cites.
“Unlocking high-accuracy differentially private image classification through scale”
Soham De et al · 2022
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
“Reconstructing training data with informed adversaries”
Borja Balle, Giovanni Cherubin and Jamie Hayes · 2022
Cited alongside, same era.
“Bounding training data reconstruction in private (deep) learning”
Chuan Guo, Brian Karrer, Kamalika Chaudhuri and Laurens van Maaten · 2022
Cited alongside, same era.
“Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano”
Chuan Guo, Alexandre Sablayrolles and Maziar Sanjabi · 2022
Cited alongside, same era.
Later among the works it cites.
“Extracting training data from diffusion models”
Nicholas Carlini et al · 2023
Closest in time.
“Bounding Training Data Reconstruction in DP-SGD”
Jamie Hayes, Saeed Mahloujifar and Borja Balle · 2023
Closest in time.
“mpmath: a Python library for arbitrary-precision floating-point arithmetic (version 1.3.0)” http://mpmath.org/
The mpmath team · 2023
Closest in time.
“A Randomized Approach for Tight Privacy Accounting”
Jiachen Wang et al · 2023
Closest in time.