We investigate the local differential privacy (LDP) guarantees of a randomized privacy mechanism via its contraction properties. We first show that LDP constraints can be equivalently cast in terms of the contraction coefficient of the $E_γ$-divergence. We then use this equivalent formula to express LDP guarantees of privacy mechanisms in terms of contraction coefficients of arbitrary $f$-divergences. When combined with standard estimation-theoretic tools (such as Le Cam's and Fano's converse methods), this result allows us to study the trade-off between privacy and utility in several testing and minimax and Bayesian estimation problems.
Courant Institute of Mathematical Sciences, New York University（纽约大学库朗数学科学研究所）；IBM Research AI（IBM研究院人工智能部门）
Differential privacy (DP) is the de facto standard for private data release and private machine learning. Auditing black-box DP algorithms and mechanisms to certify whether they satisfy a certain DP guarantee is challenging, especially in high dimension. We propose relaxations of differential privacy based on new divergences on probability distributions: the kernel Rényi divergence and its regularized version. We show that the regularized kernel Rényi divergence can be estimated from samples even in high dimensions, giving rise to auditing procedures for $\varepsilon$-DP, $(\varepsilon,δ)$-DP …
Amazon Research（亚马逊研究院）；IMDEA Software Institute（IMDEA软件研究所）；University at Buffalo (SUNY)（布法罗大学（纽约州立大学））
Differential privacy comes equipped with multiple analytical tools for the design of private data analyses. One important tool is the so-called "privacy amplification by subsampling" principle, which ensures that a differentially private mechanism run on a random subsample of a population provides higher privacy guarantees than when run on the entire population. Several instances of this principle have been studied for different random subsampling methods, each with an ad-hoc analysis. In this paper we present a general method that recovers and improves prior analyses, yields lower bounds and …
Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization
State Key Laboratory of Internet of Things for Smart City and the Department of Electrical and Computer Engineering, University of Macau（物联网智能城市国家重点实验室和澳门大学电子与计算机工程系）；Department of Electrical and Computer Engineering, Cornell Tech, Cornell University（电气与计算机工程系，康奈尔科技，康奈尔大学）；Computing Sciences Research, Lawrence Berkeley National Laboratory（计算科学研究所，劳伦斯伯克利国家实验室）
Quantum Information Ordering and Differential Privacy
Indian Statistical Institute（印度统计研究所）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学深圳校区数据科学学院）；International Quantum Academy（国际量子学院）；Graduate School of Mathematics, Nagoya University（名古屋大学数学研究生院）
Non-Linear Strong Data-Processing for Quantum Hockey-Stick Divergences
Department of Mathematics and Illinois Quantum Information Science and Technology (IQUIST) Center, University of Illinois Urbana-Champaign（数学系和伊利诺伊大学量子信息科学与技术中心，伊利诺伊大学厄巴纳-香槟分校）；Centre for Quantum Technologies, National University of Singapore（新加坡国立大学量子技术中心）；Institute for Information Processing (tnt/L3S), Leibniz Universität Hannover（汉诺威莱布尼茨信息处理研究所（tnt/L3S））
"Concentrated differential privacy" was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many privacy-preserving computations. We present an alternative formulation of the concept of concentrated differential privacy in terms of the Renyi divergence between the distributions obtained by running an algorithm on neighboring inputs. With this reformulation in hand, we prove sharper quantitative results, establish lower bounds, and raise a few new questions. We also unify this approach with approximate differential privacy by givi…
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…
Université Paris-Dauphine, PSL Research University（巴黎第九大学，PSL研究大学）；Institut LIST, CEA（法国原子能与替代能源委员会LIST研究所）；Université Paris-Saclay（巴黎萨克雷大学）
This short note highlights some links between two lines of research within the emerging topic of trustworthy machine learning: differential privacy and robustness to adversarial examples. By abstracting the definitions of both notions, we show that they build upon the same theoretical ground and hence results obtained so far in one domain can be transferred to the other. More precisely, our analysis is based on two key elements: probabilistic mappings (also called randomized algorithms in the differential privacy community), and the Renyi divergence which subsumes a large family of divergences…
Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
Department of Electrical Engineering, National Taiwan University, Taiwan（台湾国立台湾大学电子工程系）；NTU Artificial Intelligence Center of Research Excellence (NTU AI-CoRE), Taiwan（国立台湾大学人工智能研究中心（NTU AI-CoRE））；Microsoft, USA（微软公司）；Department of Electrical and Computer Engineering, Georgia Institute of Technology, USA（佐治亚理工学院电子与计算机工程系）
Harvard University（哈佛大学）；Universidad Nacional Autónoma de México（墨西哥国立自治大学）
We investigate the framework of privacy amplification by iteration, recently proposed by Feldman et al., from an information-theoretic lens. We demonstrate that differential privacy guarantees of iterative mappings can be determined by a direct application of contraction coefficients derived from strong data processing inequalities for $f$-divergences. In particular, by generalizing the Dobrushin's contraction coefficient for total variation distance to an $f$-divergence known as $E_γ$-divergence, we derive tighter bounds on the differential privacy parameters of the projected noisy stochastic…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Waterloo（滑铁卢大学）；NVIDIA（英伟达）
Although machine learning models trained on massive data have led to break-throughs in several areas, their deployment in privacy-sensitive domains remains limited due to restricted access to data. Generative models trained with privacy constraints on private data can sidestep this challenge, providing indirect access to private data instead. We propose DP-Sinkhorn, a novel optimal transport-based generative method for learning data distributions from private data with differential privacy. DP-Sinkhorn minimizes the Sinkhorn divergence, a computationally efficient approximation to the exact op…
Individual Privacy Accounting with Gaussian Differential Privacy
Nokia Bell Labs（诺基亚贝尔实验室）；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）；Department of Computer Science, University of Helsinki（赫尔辛基大学计算机科学系）
Harvard University（哈佛大学）；Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas (IIMAS), Universidad Nacional Autónoma de México（墨西哥国立自治大学应用数学与系统研究所（IIMAS））
We investigate the contraction coefficients derived from strong data processing inequalities for the $E_γ$-divergence. By generalizing the celebrated Dobrushin's coefficient from total variation distance to $E_γ$-divergence, we derive a closed-form expression for the contraction of $E_γ$-divergence. This result has fundamental consequences in two privacy settings. First, it implies that local differential privacy can be equivalently expressed in terms of the contraction of $E_γ$-divergence. This equivalent formula can be used to precisely quantify the impact of local privacy in (Bayesian and m…
Georgia Institute of Technology（佐治亚理工学院）；University of Michigan（密歇根大学）；Google Brain（谷歌大脑）；Boston University（波士顿大学）；Northeastern University（东北大学）
In this paper, we use differential privacy as a lens to examine online learning in both full and partial information settings. The differential privacy framework is, at heart, less about privacy and more about algorithmic stability, and thus has found application in domains well beyond those where information security is central. Here we develop an algorithmic property called one-step differential stability which facilitates a more refined regret analysis for online learning methods. We show that tools from the differential privacy literature can yield regret bounds for many interesting online…
We analyse the privacy leakage of noisy stochastic gradient descent by modeling Rényi divergence dynamics with Langevin diffusions. Inspired by recent work on non-stochastic algorithms, we derive similar desirable properties in the stochastic setting. In particular, we prove that the privacy loss converges exponentially fast for smooth and strongly convex objectives under constant step size, which is a significant improvement over previous DP-SGD analyses. We also extend our analysis to arbitrary sequences of varying step sizes and derive new utility bounds. Last, we propose an implementation …
The privacy loss distribution (PLD) provides a tight characterization of the privacy loss of a mechanism in the context of differential privacy (DP). Recent work has shown that PLD-based accounting allows for tighter $(\varepsilon, δ)$-DP guarantees for many popular mechanisms compared to other known methods. A key question in PLD-based accounting is how to approximate any (potentially continuous) PLD with a PLD over any specified discrete support. We present a novel approach to this problem. Our approach supports both pessimistic estimation, which overestimates the hockey-stick divergence (i.…
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…
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 …
Various differentially private algorithms instantiate the exponential mechanism, and require sampling from the distribution $\exp(-f)$ for a suitable function $f$. When the domain of the distribution is high-dimensional, this sampling can be computationally challenging. Using heuristic sampling schemes such as Gibbs sampling does not necessarily lead to provable privacy. When $f$ is convex, techniques from log-concave sampling lead to polynomial-time algorithms, albeit with large polynomials. Langevin dynamics-based algorithms offer much faster alternatives under some distance measures such as…
Microsoft（微软）；Insitro；University of Washington（华盛顿大学）；Microsoft Research（微软研究院）
Generative machine learning models are being increasingly viewed as a way to share sensitive data between institutions. While there has been work on developing differentially private generative modeling approaches, these approaches generally lead to sub-par sample quality, limiting their use in real world applications. Another line of work has focused on developing generative models which lead to higher quality samples but currently lack any formal privacy guarantees. In this work, we propose the first formal framework for membership privacy estimation in generative models. We formulate the me…
Data processing inequalities for $f$-divergences can be sharpened using constants called "contraction coefficients" to produce strong data processing inequalities. For any discrete source-channel pair, the contraction coefficients for $f$-divergences are lower bounded by the contraction coefficient for $χ^2$-divergence. In this paper, we elucidate that this lower bound can be achieved by driving the input $f$-divergences of the contraction coefficients to zero. Then, we establish a linear upper bound on the contraction coefficients for a certain class of $f$-divergences using the contraction c…
What is the information leakage of an iterative randomized learning algorithm about its training data, when the internal state of the algorithm is \emph{private}? How much is the contribution of each specific training epoch to the information leakage through the released model? We study this problem for noisy gradient descent algorithms, and model the \emph{dynamics} of Rényi differential privacy loss throughout the training process. Our analysis traces a provably \emph{tight} bound on the Rényi divergence between the pair of probability distributions over parameters of models trained on neigh…
Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural networks subject to privacy constraints that are specified by differential privacy or its divergence-based relaxations. These privacy definitions, however, have weaknesses in handling certain important primitives (composition and subsampling), thereby giving loose or complicated privacy analyses of training neural networks. In this paper, we consider a…
Harvard University（哈佛大学）；Arizona State University（亚利桑那州立大学）
We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of Rényi differential privacy (RDP). Our result is based on the joint range of two $f$-divergences that underlie the approximate and the Rényi variations of differential privacy. We apply our result to the moments accountant framework for characterizing privacy guarantees of stochastic gradient descent. When compared to the state-of-the-art, our bounds may lead to about 100 more stochastic gradient descent iterations for training deep learning models for the same privacy budget.
Criteo AI Lab（Criteo人工智能实验室）；Université de Rouen Normandie（鲁昂诺曼底大学）
Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the divergences between distributions under the Differential Privacy (DP) framework -- being able to compute divergences between distributions is pivotal for many machine learning problems, such as learning generative models or domain adaptation problems. Instead of resorting to the popular gradient-based sanitization method for DP, we tackle the problem at its…
Given an empirical distribution $f(x)$ of sensitive data $x$, we consider the task of minimizing $F(y) = D_{\text{KL}} (f(x)\Vert y)$ over a probability simplex, while protecting the privacy of $x$. We observe that, if we take the exponential mechanism and use the KL divergence as the loss function, then the resulting algorithm is the Dirichlet mechanism that outputs a single draw from a Dirichlet distribution. Motivated by this, we propose a Rényi differentially private (RDP) algorithm that employs the Dirichlet mechanism to solve the KL divergence minimization task. In addition, given $f(x)$…
Harvard University（哈佛大学）；Arizona State University（亚利桑那州立大学）
We consider three different variants of differential privacy (DP), namely approximate DP, Rényi DP (RDP), and hypothesis test DP. In the first part, we develop a machinery for optimally relating approximate DP to RDP based on the joint range of two $f$-divergences that underlie the approximate DP and RDP. In particular, this enables us to derive the optimal approximate DP parameters of a mechanism that satisfies a given level of RDP. As an application, we apply our result to the moments accountant framework for characterizing privacy guarantees of noisy stochastic gradient descent (SGD). When …
Quantum Differential Privacy: An Information Theory Perspective
Technical University of Munich（慕尼黑工业大学）；National University of Singapore（新加坡国立大学）；Munich Center for Quantum Science and Technology（慕尼黑量子科学与技术中心）；University of Copenhagen（哥本哈根大学）
Google Research（谷歌研究院）；Carnegie Mellon University（卡内基梅隆大学）
We introduce the multi-dimensional Skellam mechanism, a discrete differential privacy mechanism based on the difference of two independent Poisson random variables. To quantify its privacy guarantees, we analyze the privacy loss distribution via a numerical evaluation and provide a sharp bound on the Rényi divergence between two shifted Skellam distributions. While useful in both centralized and distributed privacy applications, we investigate how it can be applied in the context of federated learning with secure aggregation under communication constraints. Our theoretical findings and extensi…
Tight Contraction Rates for Primitive Channels under Quantum $f$-Divergences
School of Computing National University of Singapore Singapore 117417, Singapore；Computer Engineering \& Centre for Quantum Technologies National University of Singapore Singapore 117543, Singapore；Centre for Quantum Technologies National University of Singapore Singapore 117543, Singapore
