Plausible Deniability for Privacy-Preserving Data Synthesis

By Vincent Bindschaedler, Reza Shokri, Carl A. Gunter. 2017

178 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Prochlo: Strong Privacy for Analytics in the Crowd (2017, background): “, a crowd), for reports to blend into [10, 33, 45].”
Scalable Private Learning with PATE (2018, background): “This is not the case of all privacy definitions, as demonstrated by successful attacks against anonymization techniques (Aggarwal, 2005; Narayanan & Shmatikov, 2008; Bindschaedler et al., 2017).”
PROCHLO: Strong Privacy for Analytics in the Crowd (2017, background): “, a crowd), for reports to blend into [10, 33, 45].”
Local Differential Privacy-Based Federated Learning for Internet of Things (2020, unknown): “To address these concerns, we propose a hybrid approach that integrates federated learning (FL) [1] with local differential privacy (LDP) [2] techniques.”
Generating Differentially Private Datasets Using GANs (2018, methodology): “This direction is taken, for example, by Bindschaedler et al. (2017).”
Machine Learning for Synthetic Data Generation: a Review (2023, methodology): “In the second category, synthetic data generation approaches have been proposed to generate realistic synthetic data using rigorous differential privacy definitions [113], [165], [184] for various applications.”
Differentially Private SQL with Bounded User Contribution (2019, methodology): “In this work, for clarity, we keep the description of our system conceptually simple, and explicitly do not make use of techniques like smooth sensitivity [39], tight privacy budget computation methods [22, 34], variants of the differential privacy definition [6, 8, 36], adjustment of noise levels t”
Synthetic Data for Social Good (2017, methodology): “Other recent approaches in privacy-preserving data generation include the work on plausible deniability in data synthesis [4], on perturbed Gibbs sampling for private data release [19, 18], and on sampling from differentially private copula functions [14].”
Differentially Private Mixture of Generative Neural Networks (2017, methodology): “ [9,32,33,59]. In this paper, we follow this approach, while, in a ﬁrst-of-its-kind attempt, focusing on building private generative machine learning models based on neural networks. Other approaches [7,39,40] generate data records ﬁrst, and then attempt to test their privacy guarantees, i.e., decou”