skip to main content

Title: Utility Analysis of Horizontally Merged Multi-Party Synthetic Data with Differential Privacy
A large amount of data is often needed to train machine learning algorithms with confidence. One way to achieve the necessary data volume is to share and combine data from multiple parties. On the other hand, how to protect sensitive personal information during data sharing is always a challenge. We focus on data sharing when parties have overlapping attributes but non-overlapping individuals. One approach to achieve privacy protection is through sharing differentially private synthetic data. Each party generates synthetic data at its own preferred privacy budget, which is then released and horizontally merged across the parties. The total privacy cost for this approach is capped at the maximum individual budget employed by a party. We derive the mean squared error bounds for the parameter estimation in common regression analysis based on the merged sanitized data across parties. We identify through theoretical analysis the conditions under which the utility of sharing and merging sanitized data outweighs the perturbation introduced for satisfying differential privacy and surpasses that based on individual party data. The experiments suggest that sanitized HOMM data obtained at a practically reasonable small privacy cost can lead to smaller prediction and estimation errors than individual parties, demonstrating the benefits of more » data sharing while protecting privacy. « less
Authors:
;
Award ID(s):
1717417
Publication Date:
NSF-PAR ID:
10311785
Journal Name:
2020 IEEE International Symposium on Networks, Computers and Communications (ISNCC)
Sponsoring Org:
National Science Foundation
More Like this
  1. Differential Privacy (DP) formalizes privacy in mathematical terms and provides a robust concept for privacy protection. DIfferentially Private Data Synthesis (DIPS) techniques produce and release synthetic individual-level data in the DP framework. One key challenge to develop DIPS methods is the preservation of the statistical utility of synthetic data, especially in high-dimensional settings. We propose a new DIPS approach, STatistical Election to Partition Sequentially (STEPS) that partitions data by attributes according to their importance ranks according to either a practical or statistical importance measure. STEPS aims to achieve better original information preservation for the attributes with higher importance ranks andmore »produce thus more useful synthetic data overall. We present an algorithm to implement the STEPS procedure and employ the privacy budget composability to ensure the overall privacy cost is controlled at the pre-specified value. We apply the STEPS procedure to both simulated data and the 2000–2012 Current Population Survey youth voter data. The results suggest STEPS can better preserve the population-level information and the original information for some analyses compared to PrivBayes, a modified Uniform histogram approach, and the flat Laplace sanitizer.« less
  2. Data too sensitive to be "open" for analysis and re-purposing typically remains "closed" as proprietary information. This dichotomy undermines efforts to make algorithmic systems more fair, transparent, and accountable. Access to proprietary data in particular is needed by government agencies to enforce policy, researchers to evaluate methods, and the public to hold agencies accountable; all of these needs must be met while preserving individual privacy and firm competitiveness. In this paper, we describe an integrated legal-technical approach provided by a third-party public-private data trust designed to balance these competing interests. Basic membership allows firms and agencies to enable low-risk accessmore »to data for compliance reporting and core methods research, while modular data sharing agreements support a wide array of projects and use cases. Unless specifically stated otherwise in an agreement, all data access is initially provided to end users through customized synthetic datasets that offer a) strong privacy guarantees, b) removal of signals that could expose competitive advantage, and c) removal of biases that could reinforce discriminatory policies, all while maintaining fidelity to the original data. We find that using synthetic data in conjunction with strong legal protections over raw data strikes a balance between transparency, proprietorship, privacy, and research objectives. This legal-technical framework can form the basis for data trusts in a variety of contexts.« less
  3. Protection of individual privacy is a common concern when releasing and sharing data and information. Differential privacy (DP) formalizes privacy in probabilistic terms without making assumptions about the background knowledge of data intruders, and thus provides a robust concept for privacy protection. Practical applications of DP involve development of differentially private mechanisms to generate sanitized results at a pre-specified privacy budget. For the sanitization of statistics with publicly known bounds such as proportions and correlation coefficients, the bounding constraints will need to be incorporated in the differentially private mechanisms. There has been little work on examining the consequences of themore »bounding constraints on the accuracy of sanitized results and the statistical inferences of the population parameters based on the sanitized results. In this paper, we formalize the differentially private truncated and boundary inflated truncated (BIT) procedures for releasing statistics with publicly known bounding constraints. The impacts of the truncated and BIT Laplace procedures on the statistical accuracy and validity of sanitized statistics are evaluated both theoretically and empirically via simulation studies.« less
  4. The dominant privacy framework of the information age relies on notions of “notice and consent.” That is, service providers will disclose, often through privacy policies, their data collection practices, and users can then consent to their terms. However, it is unlikely that most users comprehend these disclosures, which is due in no small part to ambiguous, deceptive, and misleading statements. By comparing actual collection and sharing practices to disclosures in privacy policies, we demonstrate the scope of the problem. Through analysis of 68,051 apps from the Google Play Store, their corresponding privacy policies, and observed data transmissions, we investigated themore »potential misrepresentations of apps in the Designed For Families (DFF) program, inconsistencies in disclosures regarding third-party data sharing, as well as contradictory disclosures about secure data transmissions. We find that of the 8,030 DFF apps (i.e., apps directed at children), 9.1% claim that their apps are not directed at children, while 30.6% claim to have no knowledge that the received data comes from children. In addition, we observe that 10.5% of 68,051 apps share personal identifiers with third-party service providers, yet do not declare any in their privacy policies, and only 22.2% of the apps explicitly name third parties. This ultimately makes it not only difficult, but in most cases impossible, for users to establish where their personal data is being processed. Furthermore, we find that 9,424 apps do not use TLS when transmitting personal identifiers, yet 28.4% of these apps claim to take measures to secure data transfer. Ultimately, these divergences between disclosures and actual app behaviors illustrate the ridiculousness of the notice and consent framework.« less
  5. Software applications that employ secure multi-party computation (MPC) can empower individuals and organizations to benefit from privacy-preserving data analyses when data sharing is encumbered by confidentiality concerns, legal constraints, or corporate policies. MPC is already being incorporated into software solutions in some domains; however, individual use cases do not fully convey the variety, extent, and complexity of the opportunities of MPC. This position paper articulates a role-based perspective that can provide some insight into how future research directions, infrastructure development and evaluation approaches, and deployment practices for MPC may evolve. Drawing on our own lessons from existing real-world deployments andmore »the fundamental characteristics of MPC that make it a compelling technology, we propose a role-based conceptual framework for describing MPC deployment scenarios. Our framework acknowledges and leverages a novel assortment of roles that emerge from the fundamental ways in which MPC protocols support federation of functionalities and responsibilities. Defining these roles using the new opportunities for federation that MPC enables in turn can help identify and organize the capabilities, concerns, incentives, and trade-offs that affect the entities (software engineers, government regulators, corporate executives, end-users, and others) that participate in an MPC deployment scenario. This framework can not only guide the development of an ecosystem of modular and composable MPC tools, but can make explicit some of the opportunities that researchers and software engineers (and any organizations they form) have to differentiate and specialize the artifacts and services they choose to design, develop, and deploy. We demonstrate how this framework can be used to describe existing MPC deployment scenarios, how new opportunities in a scenario can be observed by disentangling roles inhabited by the involved parties, and how this can motivate the development of MPC libraries and software tools that specialize not by application domain but by role.« less