Open AccessProceedings Article
PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees
James Jordon,Jinsung Yoon,Mihaela van der Schaar +2 more
- 27 Sep 2018
TL;DR: This paper investigates a method for ensuring (differential) privacy of the generator of the Generative Adversarial Nets (GAN) framework, and modifies the Private Aggregation of Teacher Ensembles (PATE) framework and applies it to GANs.
read more
Abstract: Machine learning has the potential to assist many communities in using the large datasets that are becoming more and more available. Unfortunately, much of that potential is not being realized because it would require sharing data in a way that compromises privacy. In this paper, we investigate a method for ensuring (differential) privacy of the generator of the Generative Adversarial Nets (GAN) framework. The resulting model can be used for generating synthetic data on which algorithms can be trained and validated, and on which competitions can be conducted, without compromising the privacy of the original dataset. Our method modifies the Private Aggregation of Teacher Ensembles (PATE) framework and applies it to GANs. Our modified framework (which we call PATE-GAN) allows us to tightly bound the influence of any individual sample on the model, resulting in tight differential privacy guarantees and thus an improved performance over models with the same guarantees. We also look at measuring the quality of synthetic data from a new angle; we assert that for the synthetic data to be useful for machine learning researchers, the relative performance of two algorithms (trained and tested) on the synthetic dataset should be the same as their relative performance (when trained and tested) on the original dataset. Our experiments, on various datasets, demonstrate that PATE-GAN consistently outperforms the stateof-the-art method with respect to this and other notions of synthetic data quality.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Model Conversion via Differentially Private Data-Free Distillation
TL;DR: Differentially private data-free distillation (DPDFD) as discussed by the authors proposes a learning approach for model conversion that can convert a pretrained model (teacher) into its privacy-preserving counterpart (student) via an intermediate generator without access to training data.
2
When Synthetic Data Met Regulation
TL;DR: In this article , the authors argue that synthetic data produced by differentially private generative models can be sufficiently anonymized and, therefore, anonymous data and regulatory compliant, and they propose an anonymization scheme.
2
•Posted Content
PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning.
TL;DR: In this paper, the authors propose a framework of synthesizing data using deep generative models in a differentially private manner, where sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion.
2
Model Conversion via Differentially Private Data-Free Distillation
Bochao Liu,Pengju Wang,Shikun Li,Dan Zeng,Shiming Ge +4 more
- 01 Aug 2023
TL;DR: Model conversion via differentially private data-free distillation (DPDFD) converts a pretrained model into its privacy-preserving counterpart without access to training data.
Blender-GAN: Multi-Target Conditional Generative Adversarial Network for Novel Class Synthetic Data Generation
Akshayraj Madhubalan,Amit Gautam,Priya Tiwary +2 more
- 28 May 2024
TL;DR: This work proposes Blender-GAN, a generative adversarial network, that takes multiple class labels and their respective proportions to generate a novel output that represents all input classes in the input proportions.
2
References
Random Forests
Leo Breiman
- 01 Oct 2001
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
- 08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Latent dirichlet allocation
TL;DR: This work proposes a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hofmann's aspect model.
Greedy function approximation: A gradient boosting machine.
TL;DR: A general gradient descent boosting paradigm is developed for additive expansions based on any fitting criterion, and specific algorithms are presented for least-squares, least absolute deviation, and Huber-M loss functions for regression, and multiclass logistic likelihood for classification.
•Proceedings Article
Latent Dirichlet Allocation
David M. Blei,Andrew Y. Ng,Michael I. Jordan +2 more
- 03 Jan 2001
TL;DR: This paper proposed a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI).