arXiv subjects

Ashwin Machanavajjhala

Publications and source records attributed to Ashwin Machanavajjhala.

At least 37 records · Page 2Linked to original sources

arXiv2021

HDMM: Optimizing error of high-dimensional statistical queries under differential privacy

In this work we describe the High-Dimensional Matrix Mechanism (HDMM), a differentially private algorithm for answering a workload of predicate counting queries. HDMM represents query workloads using a compact implicit matrix representation and exploits this representation to efficiently optimize over (a subset of) the space of differentially private algorithms for one that is unbiased and answers the input query workload with low expected error. HDMM can be deployed for both $ε$-differential privacy (with Laplace noise) and $(ε, δ)$-differential privacy (with Gaussian noise), although the core techniques are slightly different for each. We demonstrate empirically that HDMM can efficiently answer queries with lower expected error than state-of-the-art techniques, and in some cases, it nearly matches existing lower bounds for the particular class of mechanisms we consider.

cs.DB↗

arXiv2021

Prior-Aware Distribution Estimation for Differential Privacy

Joint distribution estimation of a dataset under differential privacy is a fundamental problem for many privacy-focused applications, such as query answering, machine learning tasks and synthetic data generation. In this work, we examine the joint distribution estimation problem given two data points: 1) differentially private answers of a workload computed over private data and 2) a prior empirical distribution from a public dataset. Our goal is to find a new distribution such that estimating the workload using this distribution is as accurate as the differentially private answer, and the relative entropy, or KL divergence, of this distribution is minimized with respect to the prior distribution. We propose an approach based on iterative optimization for solving this problem. An application of our solution won second place in the NIST 2020 Differential Privacy Temporal Map Challenge, Sprint 2.

cs.DS↗

arXiv2021

DP-Sync: Hiding Update Patterns in Secure Outsourced Databases with Differential Privacy

In this paper, we have introduced a new type of leakage associated with modern encrypted databases called update pattern leakage. We formalize the definition and security model of DP-Sync with DP update patterns. We also proposed the framework DP-Sync, which extends existing encrypted database schemes to DP-Sync with DP update patterns. DP-Sync guarantees that the entire data update history over the outsourced data structure is protected by differential privacy. This is achieved by imposing differentially-private strategies that dictate the data owner's synchronization of local~data.

cs.CR↗

arXiv2021

Synthesizing Linked Data Under Cardinality and Integrity Constraints

The generation of synthetic data is useful in multiple aspects, from testing applications to benchmarking to privacy preservation. Generating the links between relations, subject to cardinality constraints (CCs) and integrity constraints (ICs) is an important aspect of this problem. Given instances of two relations, where one has a foreign key dependence on the other and is missing its foreign key ($FK$) values, and two types of constraints: (1) CCs that apply to the join view and (2) ICs that apply to the table with missing $FK$ values, our goal is to impute the missing $FK$ values such that the constraints are satisfied. We provide a novel framework for the problem based on declarative CCs and ICs. We further show that the problem is NP-hard and propose a novel two-phase solution that guarantees the satisfaction of the ICs. Phase I yields an intermediate solution accounting for the CCs alone, and relies on a hybrid approach based on CC types. For one type, the problem is modeled as an Integer Linear Program. For the others, we describe an efficient and accurate solution. We then combine the two solutions. Phase II augments this solution by incorporating the ICs and uses a coloring of the conflict hypergraph to infer the values of the $FK$ column. Our extensive experimental study shows that our solution scales well when the data and number of constraints increases. We further show that our solution maintains low error rates for the CCs.

cs.DB↗

arXiv2020

DP-Cryptography: Marrying Differential Privacy and Cryptography in Emerging Applications

Differential privacy (DP) has arisen as the state-of-the-art metric for quantifying individual privacy when sensitive data are analyzed, and it is starting to see practical deployment in organizations such as the US Census Bureau, Apple, Google, etc. There are two popular models for deploying differential privacy - standard differential privacy (SDP), where a trusted server aggregates all the data and runs the DP mechanisms, and local differential privacy (LDP), where each user perturbs their own data and perturbed data is analyzed. Due to security concerns arising from aggregating raw data at a single server, several real world deployments in industry have embraced the LDP model. However, systems based on the LDP model tend to have poor utility - "a gap" in the utility achieved as compared to systems based on the SDP model. In this work, we survey and synthesize emerging directions of research at the intersection of differential privacy and cryptography. First, we survey solutions that combine cryptographic primitives like secure computation and anonymous communication with differential privacy to give alternatives to the LDP model that avoid a trusted server as in SDP but close the gap in accuracy. These primitives introduce performance bottlenecks and necessitate efficient alternatives. Second, we synthesize work in an area we call "DP-Cryptography" - cryptographic primitives that are allowed to leak differentially private outputs. These primitives have orders of magnitude better performance than standard cryptographic primitives. DP-cryptographic primitives are perfectly suited for implementing alternatives to LDP, but are also applicable to scenarios where standard cryptographic primitives do not have practical implementations. Through this unique lens of research taxonomy, we survey ongoing research in these directions while also providing novel directions for future research.

cs.CR↗

arXiv2020

Computing Local Sensitivities of Counting Queries with Joins

Local sensitivity of a query Q given a database instance D, i.e. how much the output Q(D) changes when a tuple is added to D or deleted from D, has many applications including query analysis, outlier detection, and in differential privacy. However, it is NP-hard to find local sensitivity of a conjunctive query in terms of the size of the query, even for the class of acyclic queries. Although the complexity is polynomial when the query size is fixed, the naive algorithms are not efficient for large databases and queries involving multiple joins. In this paper, we present a novel approach to compute local sensitivity of counting queries involving join operations by tracking and summarizing tuple sensitivities -- the maximum change a tuple can cause in the query result when it is added or removed. We give algorithms for the sensitivity problem for full acyclic join queries using join trees, that run in polynomial time in both the size of the database and query for an interesting sub-class of queries, which we call 'doubly acyclic queries' that include path queries, and in polynomial time in combined complexity when the maximum degree in the join tree is bounded. Our algorithms can be extended to certain non-acyclic queries using generalized hypertree decompositions. We evaluate our approach experimentally, and show applications of our algorithms to obtain better results for differential privacy by orders of magnitude.

cs.DB↗

arXiv2020

Crypt$ε$: Crypto-Assisted Differential Privacy on Untrusted Servers

Differential privacy (DP) has steadily become the de-facto standard for achieving privacy in data analysis, which is typically implemented either in the "central" or "local" model. The local model has been more popular for commercial deployments as it does not require a trusted data collector. This increased privacy, however, comes at a cost of utility and algorithmic expressibility as compared to the central model. In this work, we propose, Crypt$ε$, a system and programming framework that (1) achieves the accuracy guarantees and algorithmic expressibility of the central model (2) without any trusted data collector like in the local model. Crypt$ε$ achieves the "best of both worlds" by employing two non-colluding untrusted servers that run DP programs on encrypted data from the data owners. Although straightforward implementations of DP programs using secure computation tools can achieve the above goal theoretically, in practice they are beset with many challenges such as poor performance and tricky security proofs. To this end, Crypt$ε$ allows data analysts to author logical DP programs that are automatically translated to secure protocols that work on encrypted data. These protocols ensure that the untrusted servers learn nothing more than the noisy outputs, thereby guaranteeing DP (for computationally bounded adversaries) for all Crypt$ε$ programs. Crypt$ε$ supports a rich class of DP programs that can be expressed via a small set of transformation and measurement operators followed by arbitrary post-processing. Further, we propose performance optimizations leveraging the fact that the output is noisy. We demonstrate Crypt$ε$'s feasibility for practical DP analysis with extensive empirical evaluations on real datasets.

cs.CR↗

arXiv2020

Fair Decision Making using Privacy-Protected Data

Data collected about individuals is regularly used to make decisions that impact those same individuals. We consider settings where sensitive personal data is used to decide who will receive resources or benefits. While it is well known that there is a tradeoff between protecting privacy and the accuracy of decisions, we initiate a first-of-its-kind study into the impact of formally private mechanisms (based on differential privacy) on fair and equitable decision-making. We empirically investigate novel tradeoffs on two real-world decisions made using U.S. Census data (allocation of federal funds and assignment of voting rights benefits) as well as a classic apportionment problem. Our results show that if decisions are made using an $ε$-differentially private version of the data, under strict privacy constraints (smaller $ε$), the noise added to achieve privacy may disproportionately impact some groups over others. We propose novel measures of fairness in the context of randomized differentially private algorithms and identify a range of causes of outcome disparities.

cs.DB↗

arXiv2019

Answering Summation Queries for Numerical Attributes under Differential Privacy

In this work we explore the problem of answering a set of sum queries under Differential Privacy. This is a little understood, non-trivial problem especially in the case of numerical domains. We show that traditional techniques from the literature are not always the best choice and a more rigorous approach is necessary to develop low error algorithms.

cs.DB↗

arXiv2019

Capacity Bounded Differential Privacy

Differential privacy, a notion of algorithmic stability, is a gold standard for measuring the additional risk an algorithm's output poses to the privacy of a single record in the dataset. Differential privacy is defined as the distance between the output distribution of an algorithm on neighboring datasets that differ in one entry. In this work, we present a novel relaxation of differential privacy, capacity bounded differential privacy, where the adversary that distinguishes output distributions is assumed to be capacity-bounded -- i.e. bounded not in computational power, but in terms of the function class from which their attack algorithm is drawn. We model adversaries in terms of restricted f-divergences between probability distributions, and study properties of the definition and algorithms that satisfy them.

cs.LG↗

arXiv2019

Ektelo: A Framework for Defining Differentially-Private Computations

The adoption of differential privacy is growing but the complexity of designing private, efficient and accurate algorithms is still high. We propose a novel programming framework and system, Ektelo, for implementing both existing and new privacy algorithms. For the task of answering linear counting queries, we show that nearly all existing algorithms can be composed from operators, each conforming to one of a small number of operator classes. While past programming frameworks have helped to ensure the privacy of programs, the novelty of our framework is its significant support for authoring accurate and efficient (as well as private) programs. After describing the design and architecture of the Ektelo system, we show that Ektelo is expressive, allows for safer implementations through code reuse, and that it allows both privacy novices and experts to easily design algorithms. We demonstrate the use of Ektelo by designing several new state-of-the-art algorithms.

cs.DB↗

arXiv2019

APEx: Accuracy-Aware Differentially Private Data Exploration

Organizations are increasingly interested in allowing external data scientists to explore their sensitive datasets. Due to the popularity of differential privacy, data owners want the data exploration to ensure provable privacy guarantees. However, current systems for answering queries with differential privacy place an inordinate burden on the data analysts to understand differential privacy, manage their privacy budget, and even implement new algorithms for noisy query answering. Moreover, current systems do not provide any guarantees to the data analyst on the quality they care about, namely accuracy of query answers. We present APEx, a novel system that allows data analysts to pose adaptively chosen sequences of queries along with required accuracy bounds. By translating queries and accuracy bounds into differentially private algorithms with the least privacy loss, APEx returns query answers to the data analyst that meet the accuracy bounds, and proves to the data owner that the entire data exploration process is differentially private. Our comprehensive experimental study on real datasets demonstrates that APEx can answer a variety of queries accurately with moderate to small privacy loss, and can support data exploration for entity resolution with high accuracy under reasonable privacy settings.

cs.DB↗

arXiv2018

Shrinkwrap: Differentially-Private Query Processing in Private Data Federations

A private data federation is a set of autonomous databases that share a unified query interface offering in-situ evaluation of SQL queries over the union of the sensitive data of its members. Owing to privacy concerns, these systems do not have a trusted data collector that can see all their data and their member databases cannot learn about individual records of other engines. Federations currently achieve this goal by evaluating queries obliviously using secure multiparty computation. This hides the intermediate result cardinality of each query operator by exhaustively padding it. With cascades of such operators, this padding accumulates to a blow-up in the output size of each operator and a proportional loss in query performance. Hence, existing private data federations do not scale well to complex SQL queries over large datasets. We introduce Shrinkwrap, a private data federation that offers data owners a differentially private view of the data held by others to improve their performance over oblivious query processing. Shrinkwrap uses computational differential privacy to minimize the padding of intermediate query results, achieving up to 35X performance improvement over oblivious query processing. When the query needs differentially private output, Shrinkwrap provides a trade-off between result accuracy and query evaluation performance.

cs.DB↗

arXiv2018

Differentially Private Hierarchical Count-of-Counts Histograms

We consider the problem of privately releasing a class of queries that we call hierarchical count-of-counts histograms. Count-of-counts histograms partition the rows of an input table into groups (e.g., group of people in the same household), and for every integer j report the number of groups of size j. Hierarchical count-of-counts queries report count-of-counts histograms at different granularities as per hierarchy defined on an attribute in the input data (e.g., geographical location of a household at the national, state and county levels). In this paper, we introduce this problem, along with appropriate error metrics and propose a differentially private solution that generates count-of-counts histograms that are consistent across all levels of the hierarchy.

cs.DB↗

arXiv2018

Optimizing error of high-dimensional statistical queries under differential privacy

Differentially private algorithms for answering sets of predicate counting queries on a sensitive database have many applications. Organizations that collect individual-level data, such as statistical agencies and medical institutions, use them to safely release summary tabulations. However, existing techniques are accurate only on a narrow class of query workloads, or are extremely slow, especially when analyzing more than one or two dimensions of the data. In this work we propose HDMM, a new differentially private algorithm for answering a workload of predicate counting queries, that is especially effective for higher-dimensional datasets. HDMM represents query workloads using an implicit matrix representation and exploits this compact representation to efficiently search (a subset of) the space of differentially private algorithms for one that answers the input query workload with high accuracy. We empirically show that HDMM can efficiently answer queries with lower error than state-of-the-art techniques on a variety of low and high dimensional datasets.

cs.DB↗

arXiv2018

Providing Access to Confidential Research Data Through Synthesis and Verification: An Application to Data on Employees of the U.S. Federal Government

Data stewards seeking to provide access to large-scale social science data face a difficult challenge. They have to share data in ways that protect privacy and confidentiality, are informative for many analyses and purposes, and are relatively straightforward to use by data analysts. One approach suggested in the literature is that data stewards generate and release synthetic data, i.e., data simulated from statistical models, while also providing users access to a verification server that allows them to assess the quality of inferences from the synthetic data. We present an application of the synthetic data plus verification server approach to longitudinal data on employees of the U.S. federal government. As part of the application, we present a novel model for generating synthetic career trajectories, as well as strategies for generating high dimensional, longitudinal synthetic datasets. We also present novel verification algorithms for regression coefficients that satisfy differential privacy. We illustrate the integrated use of synthetic data plus verification via analysis of differentials in pay by race. The integrated system performs as intended, allowing users to explore the synthetic data for potential pay differentials and learn through verifications which findings in the synthetic data hold up and which do not. The analysis on the confidential data reveals pay differentials across races not documented in published studies.

stat.AP↗

arXiv2018

Differentially private significance tests for regression coefficients

Many data producers seek to provide users access to confidential data without unduly compromising data subjects' privacy and confidentiality. One general strategy is to require users to do analyses without seeing the confidential data; for example, analysts only get access to synthetic data or query systems that provide disclosure-protected outputs of statistical models. With synthetic data or redacted outputs, the analyst never really knows how much to trust the resulting findings. In particular, if the user did the same analysis on the confidential data, would regression coefficients of interest be statistically significant or not? We present algorithms for assessing this question that satisfy differential privacy. We describe conditions under which the algorithms should give accurate answers about statistical significance. We illustrate the properties of the proposed methods using artificial and genuine data.

stat.ME↗

arXiv2017

One-sided Differential Privacy

In this paper, we study the problem of privacy-preserving data sharing, wherein only a subset of the records in a database are sensitive, possibly based on predefined privacy policies. Existing solutions, viz, differential privacy (DP), are over-pessimistic and treat all information as sensitive. Alternatively, techniques, like access control and personalized differential privacy, reveal all non-sensitive records truthfully, and they indirectly leak information about sensitive records through exclusion attacks. Motivated by the limitations of prior work, we introduce the notion of one-sided differential privacy (OSDP). We formalize the exclusion attack and we show how OSDP protects against it. OSDP offers differential privacy like guarantees, but only to the sensitive records. OSDP allows the truthful release of a subset of the non-sensitive records. The sample can be used to support applications that must output true data, and is well suited for publishing complex types of data, e.g. trajectories. Though some non-sensitive records are suppressed to avoid exclusion attacks, our experiments show that the suppression results in a small loss in utility in most cases. Additionally, we present a recipe for turning DP mechanisms for answering counting queries into OSDP techniques for the same task. Our OSDP algorithms leverage the presence of non-sensitive records and are able to offer up to a 25x improvement in accuracy over state-of-the-art DP-solutions.

cs.CR↗