skip to main content


Title: MGD: A Utility Metric for Private Data Publication
techniques to protect user data privacy. A common way for utilizing private data under DP is to take an input dataset and synthesize a new dataset that preserves features of the input dataset while satisfying DP. A trade-off always exists between the strength of privacy protection and the utility of the final output: stronger privacy protection requires larger randomness, so the outputs usually have a larger variance and can be far from optimal. In this paper, we summarize our proposed metric for the NIST “A Better Meter Stick for Differential Privacy” competition [26], MarGinal Difference (MGD), for measuring the utility of a synthesized dataset. Our metric is based on earth mover distance. We introduce new features in our metric so that it is not affected by some small random noise that is unavoidable in the DP context but focuses more on the significant difference. We show that our metric can reflect the range query error better compared with other existing metrics. We introduce an efficient computation method based on the min-cost flow to alleviate the high computation cost of the earth mover’s distance.  more » « less
Award ID(s):
1931443
NSF-PAR ID:
10322949
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
NSysS 2021: Proceedings of the 8th International Conference on Networking, Systems and Security
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Differential privacy (DP) is a widely used notion for reasoning about privacy when publishing aggregate data. In this paper, we observe that certain DP mechanisms are amenable to a posteriori privacy analysis that exploits the fact that some outputs leak less information about the input database than others. To exploit this phenomenon, we introduce output differential privacy (ODP) and a new composition experiment, and leverage these new constructs to obtain significant privacy budget savings and improved privacy–utility tradeoffs under composition. All of this comes at no cost in terms of privacy; we do not weaken the privacy guarantee. To demonstrate the applicability of our a posteriori privacy analysis techniques, we analyze two well-known mechanisms: the Sparse Vector Technique and the Propose-Test-Release framework. We then show how our techniques can be used to save privacy budget in more general contexts: when a differentially private iterative mechanism terminates before its maximal number of iterations is reached, and when the output of a DP mechanism provides unsatisfactory utility. Examples of the former include iterative optimization algorithms, whereas examples of the latter include training a machine learning model with a large generalization error. Our techniques can be applied beyond the current paper to refine the analysis of existing DP mechanisms or guide the design of future mechanisms. 
    more » « less
  2. Label differential privacy is a relaxation of differential privacy for machine learning scenarios where the labels are the only sensitive information that needs to be protected in the training data. For example, imagine a survey from a participant in a university class about their vaccination status. Some attributes of the students are publicly available but their vaccination status is sensitive information and must remain private. Now if we want to train a model that predicts whether a student has received vaccination using only their public information, we can use label-DP. Recent works on label-DP use different ways of adding noise to the labels in order to obtain label-DP models. In this work, we present novel techniques for training models with label-DP guarantees by leveraging unsupervised learning and semi-supervised learning, enabling us to inject less noise while obtaining the same privacy, therefore achieving a better utility-privacy trade-off. We first introduce a framework that starts with an unsupervised classifier f0 and dataset D with noisy label set Y , reduces the noise in Y using f0 , and then trains a new model f using the less noisy dataset. Our noise reduction strategy uses the model f0 to remove the noisy labels that are incorrect with high probability. Then we use semi-supervised learning to train a model using the remaining labels. We instantiate this framework with multiple ways of obtaining the noisy labels and also the base classifier. As an alternative way to reduce the noise, we explore the effect of using unsupervised learning: we only add noise to a majority voting step for associating the learned clusters with a cluster label (as opposed to adding noise to individual labels); the reduced sensitivity enables us to add less noise. Our experiments show that these techniques can significantly outperform the prior works on label-DP. 
    more » « less
  3. 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 and 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. 
    more » « less
  4. Introduction

    Big graphs like social network user interactions and customer rating matrices require significant computing resources to maintain. Data owners are now using public cloud resources for storage and computing elasticity. However, existing solutions do not fully address the privacy and ownership protection needs of the key involved parties: data contributors and the data owner who collects data from contributors.

    Methods

    We propose a Trusted Execution Environment (TEE) based solution: TEE-Graph for graph spectral analysis of outsourced graphs in the cloud. TEEs are new CPU features that can enable much more efficient confidential computing solutions than traditional software-based cryptographic ones. Our approach has several unique contributions compared to existing confidential graph analysis approaches. (1) It utilizes the unique TEE properties to ensure contributors' new privacy needs, e.g., the right of revocation for shared data. (2) It implements efficient access-pattern protection with a differentially private data encoding method. And (3) it implements TEE-based special analysis algorithms: the Lanczos method and the Nystrom method for efficiently handling big graphs and protecting confidentiality from compromised cloud providers.

    Results

    The TEE-Graph approach is much more efficient than software crypto approaches and also immune to access-pattern-based attacks. Compared with the best-known software crypto approach for graph spectral analysis, PrivateGraph, we have seen that TEE-Graph has 103−105times lower computation, storage, and communication costs. Furthermore, the proposed access-pattern protection method incurs only about 10%-25% of the overall computation cost.

    Discussion

    Our experimentation showed that TEE-Graph performs significantly better and has lower costs than typical software approaches. It also addresses the unique ownership and access-pattern issues that other TEE-related graph analytics approaches have not sufficiently studied. The proposed approach can be extended to other graph analytics problems with strong ownership and access-pattern protection.

     
    more » « less
  5. Gørtz, Inge Li ; Farach-Colton, Martin ; Puglisi, Simon J. ; Herman, Grzegorz (Ed.)
    In this paper, we study efficient parallel edit distance algorithms, both in theory and in practice. Given two strings A[1..n] and B[1..m], and a set of operations allowed to edit the strings, the edit distance between A and B is the minimum number of operations required to transform A into B. In this paper, we use edit distance to refer to the Levenshtein distance, which allows for unit-cost single-character edits (insertions, deletions, substitutions). Sequentially, a standard Dynamic Programming (DP) algorithm solves edit distance with Θ(nm) cost. In many real-world applications, the strings to be compared are similar to each other and have small edit distances. To achieve highly practical implementations, we focus on output-sensitive parallel edit-distance algorithms, i.e., to achieve asymptotically better cost bounds than the standard Θ(nm) algorithm when the edit distance is small. We study four algorithms in the paper, including three algorithms based on Breadth-First Search (BFS), and one algorithm based on Divide-and-Conquer (DaC). Our BFS-based solution is based on the Landau-Vishkin algorithm. We implement three different data structures for the longest common prefix (LCP) queries needed in the algorithm: the classic solution using parallel suffix array, and two hash-based solutions proposed in this paper. Our DaC-based solution is inspired by the output-insensitive solution proposed by Apostolico et al., and we propose a non-trivial adaption to make it output-sensitive. All of the algorithms studied in this paper have good theoretical guarantees, and they achieve different tradeoffs between work (total number of operations), span (longest dependence chain in the computation), and space. We test and compare our algorithms on both synthetic data and real-world data, including DNA sequences, Wikipedia texts, GitHub repositories, etc. Our BFS-based algorithms outperform the existing parallel edit-distance implementation in ParlayLib in all test cases. On cases with fewer than 10⁵ edits, our algorithm can process input sequences of size 10⁹ in about ten seconds, while ParlayLib can only process sequences of sizes up to 10⁶ in the same amount of time. By comparing our algorithms, we also provide a better understanding of the choice of algorithms for different input patterns. We believe that our paper is the first systematic study in the theory and practice of parallel edit distance. 
    more » « less