scholarly journals Privacy and Synthetic Datasets

2018 ◽  
Author(s):  
Steven M. Bellovin ◽  
Preetam Dutta ◽  
Nathan Reitinger
Keyword(s):  
New World ◽  
Data Dissemination ◽  
Differential Privacy ◽  
Synthetic Data ◽  
Scientific Progress ◽  
Legal Implications ◽  
Database Privacy ◽  
Synthetic Datasets ◽  
Privacy Problem ◽  
Historic Approach

Sharing is a virtue, instilled in us from childhood. Unfortunately, when it comes to big data—i.e., databases possessing the potential to usher in a whole new world of scientific progress—the legal landscape prefers a hoggish motif. The historic approach to the resulting database–privacy problem has been anonymization, a subtractive technique incurring not only poor privacy results, but also lackluster utility. In anonymization’s stead, differential privacy arose; it provides better, near-perfect privacy, but is nonetheless subtractive in terms of utility. Today, another solution is leaning into the fore, synthetic data. Using the magic of machine learning, synthetic data offers a generative, additive approach—the creation of almost-but-not-quite replica data. In fact, as we recommend, synthetic data may be combined with differential privacy to achieve a best-of-both-worlds scenario. After unpacking the technical nuances of synthetic data, we analyze its legal implications, finding both over and under inclusive applications. Privacy statutes either overweigh or downplay the potential for synthetic data to leak secrets, inviting ambiguity. We conclude by finding that synthetic data is a valid, privacy-conscious alternative to raw data, but is not a cure-all for every situation. In the end, computer science progress must be met with proper policy in order to move the area of useful data dissemination forward.

scholarly journals Anonymiced Shareable Data: Using mice to Create and Analyze Multiply Imputed Synthetic Datasets

Psych ◽  
2021 ◽  
Vol 3 (4) ◽  
pp. 703-716
Author(s):  
Thom Benjamin Volker ◽  
Gerko Vink
Keyword(s):  
Data Dissemination ◽  
Simple Procedure ◽  
Synthetic Data ◽  
Ease Of Use ◽  
Private Data ◽  
Dissemination Of Research ◽  
Data Yield ◽  
Synthetic Datasets ◽  
Privacy And Confidentiality ◽  
Data Analysis Pipeline

Synthetic datasets simultaneously allow for the dissemination of research data while protecting the privacy and confidentiality of respondents. Generating and analyzing synthetic datasets is straightforward, yet, a synthetic data analysis pipeline is seldom adopted by applied researchers. We outline a simple procedure for generating and analyzing synthetic datasets with the multiple imputation software mice (Version 3.13.15) in R. We demonstrate through simulations that the analysis results obtained on synthetic data yield unbiased and valid inferences and lead to synthetic records that cannot be distinguished from the true data records. The ease of use when synthesizing data with mice along with the validity of inferences obtained through this procedure opens up a wealth of possibilities for data dissemination and further research on initially private data.

scholarly journals Statistical Disclosure Limitation: New Directions and Challenges

2018 ◽  
Vol 8 (1) ◽  
Author(s):  
Natalie Shlomo
Keyword(s):  
Data Dissemination ◽  
Differential Privacy ◽  
Synthetic Data ◽  
Remote Access ◽  
Disclosure Limitation ◽  
Disclosure Risk ◽  
Statistical Disclosure Limitation ◽  
Statistical Disclosure ◽  
Statistical Agencies ◽  
Definition Of

An overview of traditional types of data dissemination at statistical agencies is provided including definitions of disclosure risks, the quantification of disclosure risk and data utility and common statistical disclosure limitation (SDL) methods. However, with technological advancements and the increasing push by governments for openand accessible data, new forms of data dissemination are currently being explored. We focus on web-based applications such as flexible table builders and remote analysis servers, synthetic data and remote access. Many of these applications introduce new challenges for statistical agencies as they are gradually relinquishing some of their control on what data is released. There is now more recognition of the need for perturbative methods to protect the confidentiality of data subjects. These new forms of data dissemination are changing the landscape of how disclosure risks are conceptualized and the types of SDL methods that need to be applied to protect thedata. In particular, inferential disclosure is the main disclosure risk of concern and encompasses the traditional types of disclosure risks based on identity and attribute disclosures. These challenges have led to statisticians exploring the computer science definition of differential privacy and privacy- by-design applications. We explore how differential privacy can be a useful addition to the current SDL framework within statistical agencies.

scholarly journals Privacy-preserving generative deep neural networks support clinical data sharing

2017 ◽  
Author(s):  
Brett K. Beaulieu-Jones ◽  
Zhiwei Steven Wu ◽  
Chris Williams ◽  
Ran Lee ◽  
Sanjeev P. Bhavnani ◽  
...  
Keyword(s):  
Neural Networks ◽  
Data Sharing ◽  
Deep Neural Networks ◽  
Differential Privacy ◽  
Synthetic Data ◽  
Scientific Progress ◽  
Patient Privacy ◽  
Individual Level ◽  
Original Dataset ◽  
Level Data

AbstractBackgroundData sharing accelerates scientific progress but sharing individual level data while preserving patient privacy presents a barrier.Methods and ResultsUsing pairs of deep neural networks, we generated simulated, synthetic “participants” that closely resemble participants of the SPRINT trial. We showed that such paired networks can be trained with differential privacy, a formal privacy framework that limits the likelihood that queries of the synthetic participants’ data could identify a real a participant in the trial. Machine-learning predictors built on the synthetic population generalize to the original dataset. This finding suggests that the synthetic data can be shared with others, enabling them to perform hypothesis-generating analyses as though they had the original trial data.ConclusionsDeep neural networks that generate synthetic participants facilitate secondary analyses and reproducible investigation of clinical datasets by enhancing data sharing while preserving participant privacy.

scholarly journals How Can We Analyze Differentially-Private Synthetic Datasets?

2011 ◽  
Vol 2 (2) ◽  
Author(s):  
Anne-Sophie Charest
Keyword(s):  
Count Data ◽  
Differential Privacy ◽  
Synthetic Data ◽  
Data Generation ◽  
Multiple Imputations ◽  
Synthetic Data Generation ◽  
Simple Alternative ◽  
Simulation Results ◽  
Statistical Agencies ◽  
Synthetic Datasets

Synthetic datasets generated within the multiple imputation framework are now commonly used by statistical agencies to protect the confidentiality of their respondents. More recently, researchers have also proposed techniques to generate synthetic datasets which offer the formal guarantee of differential privacy. While combining rules were derived for the first type of synthetic datasets, little has been said on the analysis of differentially-private synthetic datasets generated with multiple imputations. In this paper, we show that we can not use the usual combining rules to analyze synthetic datasets which have been generated to achieve differential privacy. We consider specifically the case of generating synthetic count data with the beta-binomial synthetizer, and illustrate our discussion with simulation results. We also propose as a simple alternative a Bayesian model which models explicitly the mechanism for synthetic data generation.

scholarly journals A Privacy Preserving Algorithm to Release Sparse High-dimensional Histograms

2018 ◽  
Vol 8 (1) ◽  
Author(s):  
Bai Li ◽  
Vishesh Karwa ◽  
Aleksandra Slavković ◽  
Rebecca Carter Steorts
Keyword(s):  
Differential Privacy ◽  
Synthetic Data ◽  
Simulated Data ◽  
Estimation Algorithm ◽  
High Dimensional ◽  
Data Sets ◽  
Original Dataset ◽  
Histogram Estimation ◽  
Synthetic Datasets ◽  
Sparsity Structure

Differential privacy has emerged as a popular model to provably limit privacy risks associated with a given data release. However releasing high dimensional synthetic data under differential privacy remains a challenging problem. In this paper, we study the problem of releasing synthetic data in the form of a high dimensional histogram under the constraint of differential privacy.We develop an $(\epsilon, \delta)$-differentially private categorical data synthesizer called \emph{Stability Based Hashed Gibbs Sampler} (SBHG). SBHG works by combining a stability based sparse histogram estimation algorithm with Gibbs sampling and feature selection to approximate the empirical joint distribution of a discrete dataset. SBHG offers a competitive alternative to state-of-the art synthetic data generators while preserving the sparsity structure of the original dataset, which leads to improved statistical utility as illustrated on simulated data. Finally, to study the utility of the resulting synthetic data sets generated by SBHG, we also perform logistic regression using the synthetic datasets and compare the classification accuracy with those from using the original dataset.

scholarly journals Synthetic Data Generation with Differential Privacy via Bayesian Networks

2021 ◽  
Vol 11 (3) ◽  
Author(s):  
Ergute Bao ◽  
Xiaokui Xiao ◽  
Jun Zhao ◽  
Dongping Zhang ◽  
Bolin Ding
Keyword(s):  
Bayesian Networks ◽  
Differential Privacy ◽  
Synthetic Data ◽  
Data Generation ◽  
Synthetic Data Generation ◽  
Synthetic Datasets

This paper describes PrivBayes, a differentially private method for generating synthetic datasets that was used in the 2018 Differential Privacy Synthetic Data Challenge organized by NIST.

scholarly journals G-Tric: generating three-way synthetic datasets with triclustering solutions

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
João Lobo ◽  
Rui Henriques ◽  
Sara C. Madeira
Keyword(s):  
State Of The Art ◽  
Synthetic Data ◽  
Ground Truth ◽  
Real Data ◽  
Three Dimensions ◽  
Additional Advantage ◽  
Urban Dynamics ◽  
Data Generator ◽  
Real World Datasets ◽  
Synthetic Datasets

Abstract Background Three-way data started to gain popularity due to their increasing capacity to describe inherently multivariate and temporal events, such as biological responses, social interactions along time, urban dynamics, or complex geophysical phenomena. Triclustering, subspace clustering of three-way data, enables the discovery of patterns corresponding to data subspaces (triclusters) with values correlated across the three dimensions (observations $$\times$$ × features $$\times$$ × contexts). With increasing number of algorithms being proposed, effectively comparing them with state-of-the-art algorithms is paramount. These comparisons are usually performed using real data, without a known ground-truth, thus limiting the assessments. In this context, we propose a synthetic data generator, G-Tric, allowing the creation of synthetic datasets with configurable properties and the possibility to plant triclusters. The generator is prepared to create datasets resembling real 3-way data from biomedical and social data domains, with the additional advantage of further providing the ground truth (triclustering solution) as output. Results G-Tric can replicate real-world datasets and create new ones that match researchers needs across several properties, including data type (numeric or symbolic), dimensions, and background distribution. Users can tune the patterns and structure that characterize the planted triclusters (subspaces) and how they interact (overlapping). Data quality can also be controlled, by defining the amount of missing, noise or errors. Furthermore, a benchmark of datasets resembling real data is made available, together with the corresponding triclustering solutions (planted triclusters) and generating parameters. Conclusions Triclustering evaluation using G-Tric provides the possibility to combine both intrinsic and extrinsic metrics to compare solutions that produce more reliable analyses. A set of predefined datasets, mimicking widely used three-way data and exploring crucial properties was generated and made available, highlighting G-Tric’s potential to advance triclustering state-of-the-art by easing the process of evaluating the quality of new triclustering approaches.

scholarly journals Inferring viral occurrence patterns through a synthetic data simulation

2021 ◽  
Author(s):  
Ville N Pimenoff ◽  
Ramon Cleries
Keyword(s):  
Linear Models ◽  
Population Sample ◽  
Synthetic Data ◽  
Interaction Patterns ◽  
Viral Strain ◽  
Data Simulation ◽  
Synthetic Datasets ◽  
Pathogen Occurrence ◽  
Log Linear ◽  
Occurrence Patterns

Viruses infecting humans are manifold and several of them provoke significant morbidity and mortality. Simulations creating large synthetic datasets from observed multiple viral strain infections in a limited population sample can be a powerful tool to infer significant pathogen occurrence and interaction patterns, particularly if limited number of observed data units is available. Here, to demonstrate diverse human papillomavirus (HPV) strain occurrence patterns, we used log-linear models combined with Bayesian framework for graphical independence network (GIN) analysis. That is, to simulate datasets based on modeling the probabilistic associations between observed viral data points, i.e different viral strain infections in a set of population samples. Our GIN analysis outperformed in precision all oversampling methods tested for simulating large synthetic viral strain-level prevalence dataset from observed set of HPVs data. Altogether, we demonstrate that network modeling is a potent tool for creating synthetic viral datasets for comprehensive pathogen occurrence and interaction pattern estimations.

Sign in / Sign up

Export Citation Format

Share Document