The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets

Revealing information while preserving privacy

I. Dinur and K. Nissim · 2003

Earlier work this paper cites.

Our data, ourselves: Privacy via distributed noise generation

C. Dwork, K. Kenthapadi, F. McSherry, I. Mironov, and M. Naor · 2006

Earlier work this paper cites.

Calibrating noise to sensitivity in private data analysis

C. Dwork, F. McSherry, K. Nissim, and A. Smith · 2006

Earlier work this paper cites.

The price of privacy and the limits of LP decoding

C. Dwork, F. McSherry, and K. Talwar · 2007

Earlier work this paper cites.

New efficient attacks on statistical disclosure control mechanisms

C. Dwork and S. Yekhanin · 2008

Earlier work this paper cites.

MNIST handwritten digit database

Y. LeCun, C. Cortes, and C. Burges · 2010

Earlier work this paper cites.

Opinion on anonymisation techniques

A29WP · 2014

Earlier work this paper cites.

The algorithmic foundations of differential privacy

C. Dwork and A. Roth · 2014

Earlier work this paper cites.

Privacy in pharmacogenetics: An end-to-end case study of personalized warfarin dosing

M. Fredrikson, E. Lantz, S. Jha, S. Lin, D. Page, and T. Ristenpart · 2014

Earlier work this paper cites.

Differential privacy: an economic method for choosing epsilon

J. Hsu, M. Gaboardi, A. Haeberlen, S. Khanna, A. Narayan, B. C. Pierce, and A. Roth · 2014

Earlier work this paper cites.

Model inversion attacks that exploit confidence information and basic countermeasures

M. Fredrikson, S. Jha, and T. Ristenpart · 2015

Earlier work this paper cites.

Deep learning with differential privacy

M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang · 2016

Earlier work this paper cites.

UCI machine learning repository

D. Dua and C. Graff · 2017

Earlier work this paper cites.

Semi-supervised knowledge transfer for deep learning from private training data

N. Papernot, M. Abadi, U. Erlingsson, I. Goodfellow, and K. Talwar · 2017

Earlier work this paper cites.

DataSynthesizer: Privacy-preserving synthetic datasets

H. Ping, J. Stoyanovich, and B. Howe · 2017

Earlier work this paper cites.

Membership inference attacks against machine learning models

R. Shokri, M. Stronati, C. Song, and V. Shmatikov · 2017

Earlier work this paper cites.

Machine learning models that remember too much

C. Song, T. Ristenpart, and V. Shmatikov · 2017

Earlier work this paper cites.

PrivBayes: private data release via bayesian networks

J. Zhang, G. Cormode, C. M. Procopiuc, D. Srivastava, and X. Xiao · 2017

Earlier work this paper cites.

The creation and use of the SIPP synthetic Beta v7. 0

G. Benedetto, J. C. Stanley, E. Totty, et al · 2018

Earlier work this paper cites.

Preliminary opinion on privacy by design

EDPS · 2018

Earlier work this paper cites.

PATE-GAN: generating synthetic data with differential privacy guarantees

J. Jordon, J. Yoon, and M. Van Der Schaar · 2018

Earlier work this paper cites.

2018 Differential privacy synthetic data challenge

NIST · 2018

Earlier work this paper cites.

Privacy and data confidentiality methods: a data and analysis method review

ONS · 2018

Earlier work this paper cites.

SoK: Security and privacy in machine learning

N. Papernot, P. McDaniel, A. Sinha, and M. P. Wellman · 2018

Earlier work this paper cites.

Scalable private learning with pate

N. Papernot, S. Song, I. Mironov, A. Raghunathan, K. Talwar, and Ú. Erlingsson · 2018

Earlier work this paper cites.

Data synthesis based on generative adversarial networks

N. Park, M. Mohammadi, K. Gorde, S. Jajodia, H. Park, and Y. Kim · 2018

Earlier work this paper cites.

On Location, Time, and Membership: Studying How Aggregate Location Data Can Harm Users’ Privacy

A. Pyrgelis · 2018

Earlier work this paper cites.

Differentially private generative adversarial network

Original

L. Xie, K. Lin, S. Wang, F. Wang, and J. Zhou · 2018

Earlier work this paper cites.

Privacy risk in machine learning: Analyzing the connection to overfitting

S. Yeom, I. Giacomelli, M. Fredrikson, and S. Jha · 2018

Earlier work this paper cites.

Differential privacy has disparate impact on model accuracy

E. Bagdasaryan, O. Poursaeed, and V. Shmatikov · 2019

Earlier work this paper cites.

Distribution density, tails, and outliers in machine learning: Metrics and applications

Original

N. Carlini, U. Erlingsson, and N. Papernot · 2019

Earlier work this paper cites.

The secret sharer: Evaluating and testing unintended memorization in neural networks

N. Carlini, C. Liu, Ú. Erlingsson, J. Kos, and D. Song · 2019

Earlier work this paper cites.

When the signal is in the noise: Exploiting Diffix’s Sticky Noise

A. Gadotti, F. Houssiau, L. Rocher, B. Livshits, and Y.-A. De Montjoye · 2019

Earlier work this paper cites.

Understanding database reconstruction attacks on public data

S. Garfinkel, J. M. Abowd, and C. Martindale · 2019

Earlier work this paper cites.

LOGAN: membership inference attacks against generative models

J. Hayes, L. Melis, G. Danezis, and E. De Cristofaro · 2019

Earlier work this paper cites.

Monte Carlo and reconstruction membership inference attacks against generative models

B. Hilprecht, M. Härterich, and D. Bernau · 2019

Earlier work this paper cites.

Empirical evaluation on synthetic data generation with generative adversarial network

P.-H. Lu, P.-C. Wang, and C.-M. Yu · 2019

Earlier work this paper cites.

Graphical-model based estimation and inference for differential privacy

R. McKenna, D. Sheldon, and G. Miklau · 2019

Earlier work this paper cites.

Beyond inferring class representatives: User-level privacy leakage from federated learning

Z. Wang, M. Song, Z. Zhang, Y. Song, Q. Wang, and H. Qi · 2019

Earlier work this paper cites.

Detecting overfitting of deep generative networks via latent recovery

R. Webster, J. Rabin, L. Simon, and F. Jurie · 2019

Earlier work this paper cites.

Modeling tabular data using conditional gan

L. Xu, M. Skoularidou, A. Cuesta-Infante, and K. Veeramachaneni · 2019

Earlier work this paper cites.

Deep leakage from gradients

L. Zhu, Z. Liu, and S. Han · 2019

Earlier work this paper cites.

Security engineering: a guide to building dependable distributed systems

R. Anderson · 2020

Earlier work this paper cites.

GAN-Leaks: A taxonomy of membership inference attacks against generative models

D. Chen, N. Yu, Y. Zhang, and M. Fritz · 2020

Earlier work this paper cites.

Linear program reconstruction in practice

A. Cohen and K. Nissim · 2020

Earlier work this paper cites.

Towards formalizing the GDPR’s notion of singling out

A. Cohen and K. Nissim · 2020

Earlier work this paper cites.

Inverting gradients-how easy is it to break privacy in federated learning?

J. Geiping, H. Bauermeister, H. Dröge, and M. Moeller · 2020

Earlier work this paper cites.

Auditing differentially private machine learning: How private is private sgd?

M. Jagielski, J. Ullman, and A. Oprea · 2020

Earlier work this paper cites.

Truly anonymous synthetic data – evolving legal definitions and technologies (part II)

Mostly AI · 2020

Cited alongside, same era.

2020 Differential privacy temporal map challenge

NIST · 2020

Cited alongside, same era.

Practical synthetic data generation: balancing privacy and the broad availability of data

Replica Analytics · 2020

Cited alongside, same era.

Updates-leak: Data set inference and reconstruction attacks in online learning

A. M. G. Salem, A. Bhattacharyya, M. Backes, M. Fritz, and Y. Zhang · 2020

Cited alongside, same era.

Beyond privacy trade-offs with structured transparency

Original

A. Trask, E. Bluemke, B. Garfinkel, C. G. Cuervas-Mons, and A. Dafoe · 2020

Cited alongside, same era.

Analyzing information leakage of updates to natural language models

Patient-centric synthetic data generation, no reason to risk re-identification in biomedical data analysis

M. Guillaudeux, O. Rousseau, J. Petot, et al · 2023

Closest in time.

Analyzing privacy leakage in machine learning via multiple hypothesis testing: A lesson from Fano

C. Guo, A. Sablayrolles, and M. Sanjabi · 2023

Closest in time.

TabDDPM: Modelling tabular data with diffusion models

A. Kotelnikov, D. Baranchuk, I. Rubachev, and A. Babenko · 2023

Closest in time.

Arbitrary decisions are a hidden cost of differentially-private training

Original

B. Kulynych, H. Hsu, C. Troncoso, and F. P. Calmon · 2023

Closest in time.

Tabular data synthesis with generative adversarial networks: design space and optimizations

T. Liu, J. Fan, G. Li, N. Tang, and X. Du · 2023

Closest in time.