An interactive mechanism is an algorithm that stores a data set and answers adaptively chosen queries to it. The mechanism is called differentially private, if any adversary cannot distinguish whether a specific individual is in the data set by interacting with the mechanism. We study composition properties of differential privacy in concurrent compositions. In this setting, an adversary interacts with k interactive mechanisms in parallel and can interleave its queries to the mechanisms arbitrarily. Previously, Vadhan and Wang [2021] proved an optimal concurrent composition theorem for pure-differential privacy. We significantly generalize and extend their results. Namely, we prove optimal parallel composition properties for several major notions of differential privacy in the literature, including approximate DP, Rényi DP, and zero-concentrated DP. Our results demonstrate that the adversary gains no advantage by interleaving its queries to independently running mechanisms. Hence, interactivity is a feature that differential privacy grants us for free.
Concurrently and independently of our work, Vadhan and Zhang [2022] proved an optimal concurrent composition theorem for f-DP [Dong et al., 2022], which implies our result for the approximate DP case.
We study the concurrent composition properties of interactive differentially private mechanisms, whereby an adversary can arbitrarily interleave its queries to the different mechanisms. We prove that all composition theorems for non-interactive differentially private mechanisms extend to the concurrent composition of interactive differentially private mechanisms, whenever differential privacy is measured using the hypothesis testing framework of $f$-DP, which captures standard $(\eps,δ)$-DP as a special case. We prove the concurrent composition theorem by showing that every interactive $f$-DP …
We define a new interactive differentially private mechanism -- the median mechanism -- for answering arbitrary predicate queries that arrive online. Relative to fixed accuracy and privacy constraints, this mechanism can answer exponentially more queries than the previously best known interactive privacy mechanism (the Laplace mechanism, which independently perturbs each query result). Our guarantee is almost the best possible, even for non-interactive privacy mechanisms. Conceptually, the median mechanism is the first privacy mechanism capable of identifying and exploiting correlations among …
Sequential querying of differentially private mechanisms degrades the overall privacy level. In this paper, we answer the fundamental question of characterizing the level of overall privacy degradation as a function of the number of queries and the privacy levels maintained by each privatization mechanism. Our solution is complete: we prove an upper bound on the overall privacy level and construct a sequence of privatization mechanisms that achieves this bound. The key innovation is the introduction of an operational interpretation of differential privacy (involving hypothesis testing) and the…
How to query a dataset in the way of preserving the privacy of individuals whose data is included in the dataset is an important problem. The information privacy model, a variant of Shannon's information theoretic model to the encryption systems, protects the privacy of an individual by controlling the amount of information of the individual's data obtained by each adversary from the query's output. This model also assumes that each adversary's uncertainty to the queried dataset is not so small in order to improve the data utility. In this paper, we prove some results to the group privacy and …
We initiate a study of the composition properties of interactive differentially private mechanisms. An interactive differentially private mechanism is an algorithm that allows an analyst to adaptively ask queries about a sensitive dataset, with the property that an adversarial analyst's view of the interaction is approximately the same regardless of whether or not any individual's data is in the dataset. Previous studies of composition of differential privacy have focused on non-interactive algorithms, but interactive mechanisms are needed to capture many of the intended applications of differ…
We study the power of interactivity in local differential privacy. First, we focus on the difference between fully interactive and sequentially interactive protocols. Sequentially interactive protocols may query users adaptively in sequence, but they cannot return to previously queried users. The vast majority of existing lower bounds for local differential privacy apply only to sequentially interactive protocols, and before this paper it was not known whether fully interactive protocols were more powerful. We resolve this question. First, we classify locally private protocols by their composi…
Considerable attention has been paid to dynamic searchable symmetric encryption (DSSE) which allows users to search on dynamically updated encrypted databases. To improve the performance of real-world applications, recent non-interactive multi-client DSSE schemes are targeted at avoiding per-query interaction between data owners and data users. However, existing non-interactive multi-client DSSE schemes do not consider forward privacy or backward privacy, making them exposed to leakage abuse attacks. Besides, most existing DSSE schemes with forward and backward privacy rely on keeping a keywor…
Differential privacy is a promising approach to privacy preserving data analysis with a well-developed theory for functions. Despite recent work on implementing systems that aim to provide differential privacy, the problem of formally verifying that these systems have differential privacy has not been adequately addressed. This paper presents the first results towards automated verification of source code for differentially private interactive systems. We develop a formal probabilistic automaton model of differential privacy for systems by adapting prior work on differential privacy for functi…
In this paper we present ZKlaims: a system that allows users to present attribute-based credentials in a privacy-preserving way. We achieve a zero-knowledge property on the basis of Succinct Non-interactive Arguments of Knowledge (SNARKs). ZKlaims allow users to prove statements on credentials issued by trusted third parties. The credential contents are never revealed to the verifier as part of the proving process. Further, ZKlaims can be presented non-interactively, mitigating the need for interactive proofs between the user and the verifier. This allows ZKlaims to be exchanged via fully dece…
This chapter is meant to be part of the book "Differential Privacy for Artificial Intelligence Applications." We give an introduction to the most important property of differential privacy -- composition: running multiple independent analyses on the data of a set of people will still be differentially private as long as each of the analyses is private on its own -- as well as the related topic of privacy amplification by subsampling. This chapter introduces the basic concepts and gives proofs of the key results needed to apply these tools in practice.
The Sparse Vector Technique (SVT) is a fundamental technique for satisfying differential privacy and has the unique quality that one can output some query answers without apparently paying any privacy cost. SVT has been used in both the interactive setting, where one tries to answer a sequence of queries that are not known ahead of the time, and in the non-interactive setting, where all queries are known. Because of the potential savings on privacy budget, many variants for SVT have been proposed and employed in privacy-preserving data mining and publishing. However, most variants of SVT are a…
Composition is one of the most important properties of differential privacy (DP), as it allows algorithm designers to build complex private algorithms from DP primitives. We consider precise composition bounds of the overall privacy loss for exponential mechanisms, one of the fundamental classes of mechanisms in DP. We give explicit formulations of the optimal privacy loss for both the adaptive and non-adaptive settings. For the non-adaptive setting in which each mechanism has the same privacy parameter, we give an efficiently computable formulation of the optimal privacy loss. Furthermore, we…
In this paper we initiate the study of adaptive composition in differential privacy when the length of the composition, and the privacy parameters themselves can be chosen adaptively, as a function of the outcome of previously run analyses. This case is much more delicate than the setting covered by existing composition theorems, in which the algorithms themselves can be chosen adaptively, but the privacy parameters must be fixed up front. Indeed, it isn't even clear how to define differential privacy in the adaptive parameter setting. We proceed by defining two objects which cover the two mai…
Arizona State University（亚利桑那州立大学）；Harvard University（哈佛大学）；McMaster University（麦克马斯特大学）
Most differential privacy mechanisms are applied (i.e., composed) numerous times on sensitive data. We study the design of optimal differential privacy mechanisms in the limit of a large number of compositions. As a consequence of the law of large numbers, in this regime the best privacy mechanism is the one that minimizes the Kullback-Leibler divergence between the conditional output distributions of the mechanism given two different inputs. We formulate an optimization problem to minimize this divergence subject to a cost constraint on the noise. We first prove that additive mechanisms are o…
Carnegie Mellon University（卡内基梅隆大学）；California Institute of Technology（加州理工学院）；University of Pennsylvania（宾夕法尼亚大学）
In this paper we demonstrate that, ignoring computational constraints, it is possible to privately release synthetic databases that are useful for large classes of queries -- much larger in size than the database itself. Specifically, we give a mechanism that privately releases synthetic data for a class of queries over a discrete domain with error that grows as a function of the size of the smallest net approximately representing the answers to that class of queries. We show that this in particular implies a mechanism for counting queries that gives error guarantees that grow only with the VC…
Differential privacy (DP) is a widely applied paradigm for releasing data while maintaining user privacy. Its success is to a large part due to its composition property that guarantees privacy even in the case of multiple data releases. Consequently, composition has received a lot of attention from the research community: there exist several composition theorems for adversaries with different amounts of flexibility in their choice of mechanisms. But apart from mechanisms, the adversary can also choose the databases on which these mechanisms are invoked. The classic tool for analyzing the compo…
We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of privacy loss random variables to quantify the privacy loss of DP algorithms. The running time and memory needed for our algorithm to approximate the privacy curve of a DP algorithm composed with itself $k$ times is $\tilde{O}(\sqrt{k})$. This improves over the best prior method by Koskela et al. (2020) which requires $\tildeΩ(k^{1.5})$ running time. We demonstrate the utility of our algorithm by accurately computing the privacy l…
Department of Statistics（统计系）；Graduate Group in Applied Mathematics and Computational Science（应用数学与计算科学研究生组）；Department of Biostatistics, Epidemiology and Informatics（生物统计学、流行病学与信息学系）
Datasets containing sensitive information are often sequentially analyzed by many algorithms. This raises a fundamental question in differential privacy regarding how the overall privacy bound degrades under composition. To address this question, we introduce a family of analytical and sharp privacy bounds under composition using the Edgeworth expansion in the framework of the recently proposed f-differential privacy. In contrast to the existing composition theorems using the central limit theorem, our new privacy bounds under composition gain improved tightness by leveraging the refined appro…
We show that Gaussian Differential Privacy, a variant of differential privacy tailored to the analysis of Gaussian noise addition, composes gracefully even in the presence of a fully adaptive analyst. Such an analyst selects mechanisms (to be run on a sensitive data set) and their privacy budgets adaptively, that is, based on the answers from other mechanisms run previously on the same data set. In the language of Rogers, Roth, Ullman and Vadhan, this gives a filter for GDP with the same parameters as for nonadaptive composition.
With the proliferation of mobile devices and the internet of things, developing principled solutions for privacy in time series applications has become increasingly important. While differential privacy is the gold standard for database privacy, many time series applications require a different kind of guarantee, and a number of recent works have used some form of inferential privacy to address these situations. However, a major barrier to using inferential privacy in practice is its lack of graceful composition -- even if the same or related sensitive data is used in multiple releases that ar…
Privacy is an increasingly important aspect of data publishing. Reasoning about privacy, however, is fraught with pitfalls. One of the most significant is the auxiliary information (also called external knowledge, background knowledge, or side information) that an adversary gleans from other channels such as the web, public records, or domain knowledge. This paper explores how one can reason about privacy in the face of rich, realistic sources of auxiliary information. Specifically, we investigate the effectiveness of current anonymization schemes in preserving privacy when multiple organizati…
State University of New York at Buffalo（纽约州立大学布法罗分校）
In this paper, we study the Empirical Risk Minimization problem in the non-interactive local model of differential privacy. In the case of constant or low dimensionality ($p\ll n$), we first show that if the ERM loss function is $(\infty, T)$-smooth, then we can avoid a dependence of the sample complexity, to achieve error $α$, on the exponential of the dimensionality $p$ with base $1/α$ (i.e., $α^{-p}$), which answers a question in [smith 2017 interaction]. Our approach is based on polynomial approximation. Then, we propose player-efficient algorithms with $1$-bit communication complexity and…
Differential privacy (DP) provides rigorous privacy guarantees on individual's data while also allowing for accurate statistics to be conducted on the overall, sensitive dataset. To design a private system, first private algorithms must be designed that can quantify the privacy loss of each outcome that is released. However, private algorithms that inject noise into the computation are not sufficient to ensure individuals' data is protected due to many noisy results ultimately concentrating to the true, non-privatized result. Hence there have been several works providing precise formulas for h…
A key challenge facing the design of differential privacy in the non-interactive setting is to maintain the utility of the released data. To overcome this challenge, we utilize the Diaconis-Freedman-Meckes (DFM) effect, which states that most projections of high-dimensional data are nearly Gaussian. Hence, we propose the RON-Gauss model that leverages the novel combination of dimensionality reduction via random orthonormal (RON) projection and the Gaussian generative model for synthesizing differentially-private data. We analyze how RON-Gauss benefits from the DFM effect, and present multiple …
Helsinki Institute for Information Technology HIIT（赫尔辛基信息技术研究所）；University of Helsinki（赫尔辛基大学）
The recently proposed Fast Fourier Transform (FFT)-based accountant for evaluating $(\varepsilon,δ)$-differential privacy guarantees using the privacy loss distribution formalism has been shown to give tighter bounds than commonly used methods such as Rényi accountants when applied to homogeneous compositions, i.e., to compositions of identical mechanisms. In this paper, we extend this approach to heterogeneous compositions. We carry out a full error analysis that allows choosing the parameters of the algorithm such that a desired accuracy is obtained. The analysis also extends previous result…
Tel Aviv University（特拉维夫大学）；Google Research（谷歌研究院）；Technion（以色列理工学院）；Georgetown University（乔治城大学）
In this work we introduce an interactive variant of joint differential privacy towards handling online processes in which existing privacy definitions seem too restrictive. We study basic properties of this definition and demonstrate that it satisfies (suitable variants) of group privacy, composition, and post processing. We then study the cost of interactive joint privacy in the basic setting of online classification. We show that any (possibly non-private) learning rule can be effectively transformed to a private learning rule with only a polynomial overhead in the mistake bound. This demons…
University of Toronto（多伦多大学）；Columbia University（哥伦比亚大学）
We study two basic statistical tasks in non-interactive local differential privacy (LDP): learning and refutation. Learning requires finding a concept that best fits an unknown target function (from labelled samples drawn from a distribution), whereas refutation requires distinguishing between data distributions that are well-correlated with some concept in the class, versus distributions where the labels are random. Our main result is a complete characterization of the sample complexity of agnostic PAC learning for non-interactive LDP protocols. We show that the optimal sample complexity for …
University at Buffalo, SUNY（纽约州立大学布法罗分校）；Boston University（波士顿大学）
In this paper, we study the Empirical Risk Minimization (ERM) problem in the non-interactive Local Differential Privacy (LDP) model. Previous research on this problem \citep{smith2017interaction} indicates that the sample complexity, to achieve error $α$, needs to be exponentially depending on the dimensionality $p$ for general loss functions. In this paper, we make two attempts to resolve this issue by investigating conditions on the loss functions that allow us to remove such a limit. In our first attempt, we show that if the loss function is $(\infty, T)$-smooth, by using the Bernstein poly…
In this paper, we develop compositional methods for formally verifying differential privacy for algorithms whose analysis goes beyond the composition theorem. Our methods are based on the observation that differential privacy has deep connections with a generalization of probabilistic couplings, an established mathematical tool for reasoning about stochastic processes. Even when the composition theorem is not helpful, we can often prove privacy by a coupling argument. We demonstrate our methods on two algorithms: the Exponential mechanism and the Above Threshold algorithm, the critical compone…
Gaussian differential privacy (GDP) is a single-parameter family of privacy notions that provides coherent guarantees to avoid the exposure of sensitive individual information. Despite the extra interpretability and tighter bounds under composition GDP provides, many widely used mechanisms (e.g., the Laplace mechanism) inherently provide GDP guarantees but often fail to take advantage of this new framework because their privacy guarantees were derived under a different background. In this paper, we study the asymptotic properties of privacy profiles and develop a simple criterion to identify a…
Aiming at the privacy preservation of dynamic Web service composition, this paper proposes a SDN-based runtime security enforcement approach for privacy preservation of dynamic Web service composition. The main idea of this approach is that the owner of service composition leverages the security policy model (SPM) to define the access control relationships that service composition must comply with in the application plane, then SPM model is transformed into the low-level security policy model (RSPM) containing the information of SDN data plane, and RSPM model is uploaded into the SDN controlle…
In this paper, we present Zecale, a general purpose SNARK proof aggregator that uses recursive composition of SNARKs. We start by introducing the notion of recursive composition of SNARKs, before introducing Zecale as a privacy preserving scalability solution. Then, we list application types that can emerge and be built with Zecale. Finally, we argue that such scalability solutions for privacy preserving state transitions are paramount to emulate "cash" on blockchain systems.
With the development of Big Data and cloud data sharing, privacy preserving data publishing becomes one of the most important topics in the past decade. As one of the most influential privacy definitions, differential privacy provides a rigorous and provable privacy guarantee for data publishing. Differentially private interactive publishing achieves good performance in many applications; however, the curator has to release a large number of queries in a batch or a synthetic dataset in the Big Data era. To provide accurate non-interactive publishing results in the constraint of differential pr…
Differential privacy is a rigorous privacy standard that has been applied to a range of data analysis tasks. To broaden the application scenarios of differential privacy when data records have dependencies, the notion of Bayesian differential privacy has been recently proposed. However, it is unknown whether Bayesian differential privacy preserves three nice properties of differential privacy: sequential composability, parallel composability, and post-processing. In this paper, we provide an affirmative answer to this question; i.e., Bayesian differential privacy still have these properties. T…
In modern information systems different information features, about the same individual, are often collected and managed by autonomous data collection services that may have different privacy policies. Answering many end-users' legitimate queries requires the integration of data from multiple such services. However, data integration is often hindered by the lack of a trusted entity, often called a mediator, with which the services can share their data and delegate the enforcement of their privacy policies. In this paper, we propose a flexible privacy-preserving data integration approach for an…
Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses, either in handling composition of private algorithms or in analyzing important primitives like privacy amplification by subsampling. Inspired by the hypothesis testing formulation of privacy, this paper proposes a new relaxation, which we term `$f$-differential privacy' ($f$-DP). This notion of privacy has a number of appealing properties and, in particular, avo…
