Publications by Year: 2017

2017
Kobbi Nissim and Uri Stemmer. 3/2017. “Concentration Bounds for High Sensitivity Functions Through Differential Privacy”. arXiv PageAbstract

A new line of work [6, 9, 15, 2] demonstrates how differential privacy [8] can be used as a mathematical tool for guaranteeing generalization in adaptive data analysis. Specifically, if a differentially private analysis is applied on a sample S of i.i.d. examples to select a lowsensitivity function f , then w.h.p. f (S) is close to its expectation, although f is being chosen based on the data. Very recently, Steinke and Ullman [16] observed that these generalization guarantees can be used for proving concentration bounds in the non-adaptive setting, where the low-sensitivity function is fixed beforehand. In particular, they obtain alternative proofs for classical concentration bounds for low-sensitivity functions, such as the Chernoff bound and McDiarmid’s Inequality. In this work, we set out to examine the situation for functions with high-sensitivity, for which differential privacy does not imply generalization guarantees under adaptive analysis. We show that differential privacy can be used to prove concentration bounds for such functions in the non-adaptive setting.

Ezgi Cicek, Gilles Barthe, Marco Gaboardi, Deepak Garg, and Jan Hoffmann. 1/2017. “Relational Cost Analysis.” Symposium on the Principle of Programming Languages, ACM.Abstract
Establishing quantitative bounds on the execution cost of programs is essential in many areas of computer science such as complexity analysis, compiler optimizations, security and privacy. Techniques based on program analysis, type systems and abstract interpretation are well-studied, but methods for analyzing how the execution costs of two programs compare to each other have not received attention. Naively combining the worst and best case execution costs of the two programs does not work well in many cases because such analysis forgets the similarities between the programs or the inputs. In this work, we propose a relational cost analysis technique that is capable of establishing precise bounds on the difference in the execution cost of two programs by making use of relational properties of programs and inputs. We develop RelCost, a refinement type and effect system for a higher-order functional language with recursion and subtyping. The key novelty of our technique is the combination of relational refinements with two modes of typing—relational typing for reasoning about similar computations/inputs and unary typing for reasoning about unrelated computations/inputs. This combination allows us to analyze the execution cost difference of two programs more precisely than a naive non-relational approach. We prove our type system sound using a semantic model based on step-indexed unary and binary logical relations accounting for non-relational and relational reasoning principles with their respective costs. We demonstrate the precision and generality of our technique through examples.
PDF
Arthur Azevedo de Amorim, Marco Gaboardi, Justin Hsu, Shin-ya Katsumata, and Ikram Cherigui. 1/2017. “A Semantic Account of Metric Preservation.” Symposium on the Principle of Programming Languages, ACM. arXiv PageAbstract
Program sensitivity measures how robust a program is to small changes in its input, and is a fundamental notion in domains ranging from differential privacy to cyber-physical systems. A natural way to formalize program sensitivity is in terms of metrics on the input and output spaces, requiring that an r-sensitive function map inputs that are at distance d to outputs that are at distance at most r⋅d. Program sensitivity is thus an analogue of Lipschitz continuity for programs. Reed and Pierce introduced Fuzz, a functional language with a linear type system that can express program sensitivity. They show soundness operationally, in the form of a metric preservation property. Inspired by their work, we study program sensitivity and metric preservation from a denotational point of view. In particular, we introduce metric CPOs, a novel semantic structure for reasoning about computation on metric spaces, by endowing CPOs with a compatible notion of distance. This structure is useful for reasoning about metric properties of programs, and specifically about program sensitivity. We demonstrate metric CPOs by giving a model for the deterministic fragment of Fuzz.
Merce Crosas. 2017. “The DataTags System: Sharing Sensitive Data with Confidence.” Research Data Alliance (RDA) 8th Plenary on Privacy Implications of Research Data Sets, during International Data Week 2016.
Thomas Steinke and Jonathan Ullman. 2017. “Between Pure and Approximate Differential Privacy.” Journal of Privacy and Confidentiality.Abstract
We show a new lower bound on the sample complexity of (ε, δ)-differentially private algorithms that accurately answer statistical queries on high-dimensional databases. The novelty of our bound is that it depends optimally on the parameter δ, which loosely corresponds to the probability that the algorithm fails to be private, and is the first to smoothly interpolate between approximate differential privacy (δ > 0) and pure differential privacy (δ = 0).
PDF
Cynthia Dwork, Nicole Immorlica, Adam Kalai, and Max Leiserson. 2017. “Decoupled Classifiers for Fair and Efficient Machine Learning.” In Fairness and Transparency in Machine Learning Conference (FATML).Abstract

When it is ethical and legal to use a sensitive attribute (such as gender or race) in machine learning systems, the question remains how to do so. We show that the naive application of machine learning algorithms using sensitive features leads to an inherent tradeoff in accuracy between groups. We provide a simple and efficient decoupling technique, that can be added on top of any black-box machine learning algorithm, to learn different classifiers for different groups. Transfer learning is used to mitigate the problem of having too little data on any one group. 

The method can apply to a range of fairness criteria. In particular, we require the application designer to specify as joint loss function that makes explicit the trade-off between fairness and accuracy. Our reduction is shown to efficiently find the minimum loss as long as the objective has a certain natural monotonicity property which may be of independent interest in the study of fairness in algorithms.

PDF
Marko Mitrovic, Mark Bun, Andreas Krause, and Amin Karbasi. 2017. “Differentially Private Submodular Maximization: Data Summarization in Disguise.” In Proceedings of the 34th International Conference on Machine Learning (ICML 2017).Abstract
Many data summarization applications are captured by the general framework of submodular maximization. As a consequence, a wide range of efficient approximation algorithms have been developed. However, when such applications involve sensitive data about individuals, their privacy concerns are not automatically addressed. To remedy this problem, we propose a general and systematic study of differentially private submodular maximization. We present privacy-preserving algorithms for both monotone and non-monotone submodular maximization under cardinality, matroid, and p-extendible system constraints, with guarantees that are competitive with optimal. Along the way, we analyze a new algorithm for non-monotone submodular maximization, which is the first (even non-privately) to achieve a constant approximation ratio while running in linear time. We additionally provide two concrete experiments to validate the efficacy of these algorithms.
PDF
Cynthia Dwork, Adam Smith, Thomas Steinke, and Jonathan Ullman. 2017. “Exposed! A Survey of Attacks on Private Data.” Annual Review of Statistics and Its Application (2017).Abstract
Privacy-preserving statistical data analysis addresses the general question of protecting privacy when publicly releasing information about a sensitive dataset. A privacy attack takes seemingly innocuous released information and uses it to discern the private details of individuals, thus demonstrating that such information compromises privacy. For example, re-identification attacks have shown that it is easy to link supposedly de-identified records to the identity of the individual concerned. This survey focuses on attacking aggregate data, such as statistics about how many individuals have a certain disease, genetic trait, or combination thereof. We consider two types of attacks: reconstruction attacks, which approximately determine a sensitive feature of all the individuals covered by the dataset, and tracing attacks, which determine whether or not a target individual's data are included in the dataset.Wealso discuss techniques from the differential privacy literature for releasing approximate aggregate statistics while provably thwarting any privacy attack.
PDF
Robert M Groves, Michael E Chernew, Piet Daas, Cynthia Dwork, Ophir Frieder, Hosagrahar V Jagadish, Frauke Kreuter, Sharon Lohr, James P Lynch, Colm O'Muircheartaigh, Trivellore Raghunathan, Roberto Rigobon, and Marc Rotenberg. 2017. “Innovations in Federal Statistics: Combining Data Sources While Protecting Privacy.” National Academies of Sciences, Engineering, and Medicine paper.Abstract
Federal government statistics provide critical information to the country and serve a key role in a democracy. For decades, sample surveys with instruments carefully designed for particular data needs have been one of the primary methods for collecting data for federal statistics. However, the costs of conducting such surveys have been increasing while response rates have been declining, and many surveys are not able to fulfill growing demands for more timely information and for more detailed information at state and local levels.
Mark Bun, Thomas Steinke, and Jonathan Ullman. 2017. “Make Up Your Mind: The Price of Online Queries in Differential Privacy.” Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA). arXiv PageAbstract

We consider the problem of answering queries about a sensitive dataset subject to differential privacy. The queries may be chosen adversarially from a larger set Q of allowable queries in one of three ways, which we list in order from easiest to hardest to answer:

• Offline: The queries are chosen all at once and the differentially private mechanism answers the queries in a single batch.

• Online: The queries are chosen all at once, but the mechanism only receives the queries in a streaming fashion and must answer each query before seeing the next query.

• Adaptive: The queries are chosen one at a time and the mechanism must answer each query before the next query is chosen. In particular, each query may depend on the answers given to previous queries.

Many differentially private mechanisms are just as efficient in the adaptive model as they are in the offline model. Meanwhile, most lower bounds for differential privacy hold in the offline setting. This suggests that the three models may be equivalent. We prove that these models are all, in fact, distinct. Specifically, we show that there is a family of statistical queries such that exponentially more queries from this family can be answered in the offline model than in the online model. We also exhibit a family of search queries such that exponentially more queries from this family can be answered in the online model than in the adaptive model. We also investigate whether such separations might hold for simple queries like threshold queries over the real line.

Michael Bar-Sinai. 2017. “Modeling Welfare Benefit Policies using the DataTags Toolset.” In European Social Policy Analysis network (ESPAnet). Israel.Abstract
We apply Tags, a framework for modeling data handling policies, to a welfare policy. The generated model is useful for assessing entitlements of specific cases, and for gaining insights into the modeled policy as a whole.
PDF
Mitali Bafna and Jonathan Ullman. 2017. “The Price of Selection in Differential Privacy.” Proceedings of The 30th Conference on Learning Theory Conference (COLT 2017). arXiv Page
Shiva Kasiviswanathan, Kobbi Nissim, and Hongxia Jin. 2017. “Private Incremental Regression.” in the ACM SIGMOD/PODS Conference (PODS 2017).
Latanya Sweeney, Ji Su Yoo, Laura Perovich, Katherine E Boronow, Phil Brown, and Julia Green Brody. 2017. “Reidentification Risks in HIPAA Safe Harbor Data: A study of data from one environmental health study.” in Technology Science.
Gustavo Durand, Michael Bar-Sinai, and Merce Crosas. 2017. “Securing Dataverse with an Adapted Command Design Pattern.” in the IEEE Secure Development Conference (IEEE 2017).
Thomas Steinke and Jonathan Ullman. 2017. “Tight Lower Bounds for Differentially Private Selection.” in the 58th Annual Symposium on Foundations of Computer Science (FOCS 2017). arXiv Page
Latanya Sweeney, Ji Su Yoo, and Jinyan Zang. 2017. “Voter Identity Theft: Submitting Changes to Voter Registrations Online to Disrupt Elections.” in Technology Science.
Cynthia Dwork. 2017. “What's Fair?” in the 23rd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2017).