Many modern statistical analysis and machine learning applications require training models on sensitive user data. Under a formal definition of privacy protection, differentially private algorithms inject calibrated noise into the confidential data or during the data analysis process to produce privacy-protected datasets or queries. However, restricting access to only privatized data during statistical analysis makes it computationally challenging to make valid statistical inferences. In this work, we propose simulation-based inference methods from privacy-protected datasets. In addition to sequential Monte Carlo approximate Bayesian computation, we adopt neural conditional density estimators as a flexible family of distributions to approximate the posterior distribution of model parameters given the observed private query results. We illustrate our methods on discrete time-series data under an infectious disease model and with ordinary linear regression models. Illustrating the privacy-utility trade-off, our experiments and analysis demonstrate the necessity and feasibility of designing valid statistical inference procedures to correct for biases introduced by the privacy-protection mechanisms.
Link prediction (LP) algorithms propose to each node a ranked list of nodes that are currently non-neighbors, as the most likely candidates for future linkage. Owing to increasing concerns about privacy, users (nodes) may prefer to keep some of their connections protected or private. Motivated by this observation, our goal is to design a differentially private LP algorithm, which trades off between privacy of the protected node-pairs and the link prediction accuracy. More specifically, we first propose a form of differential privacy on graphs, which models the privacy loss only of those node-p…
The longstanding goals of federated learning (FL) require rigorous privacy guarantees and low communication overhead while holding a relatively high model accuracy. However, simultaneously achieving all the goals is extremely challenging. In this paper, we propose a novel framework called hierarchical federated learning (H-FL) to tackle this challenge. Considering the degradation of the model performance due to the statistic heterogeneity of the training data, we devise a runtime distribution reconstruction strategy, which reallocates the clients appropriately and utilizes mediators to rearran…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（图宾根大学）；Google Research（谷歌研究院）
We develop a novel approximate Bayesian computation (ABC) framework, ABCDP, that produces differentially private (DP) and approximate posterior samples. Our framework takes advantage of the Sparse Vector Technique (SVT), widely studied in the differential privacy literature. SVT incurs the privacy cost only when a condition (whether a quantity of interest is above/below a threshold) is met. If the condition is met sparsely during the repeated queries, SVT can drastically reduces the cumulative privacy loss, unlike the usual case where every query incurs the privacy loss. In ABC, the quantity o…
Artificial Intelligence Lab, Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院人工智能实验室）
Traditional differential privacy is independent of the data distribution. However, this is not well-matched with the modern machine learning context, where models are trained on specific data. As a result, achieving meaningful privacy guarantees in ML often excessively reduces accuracy. We propose Bayesian differential privacy (BDP), which takes into account the data distribution to provide more practical privacy guarantees. We also derive a general privacy accounting method under BDP, building upon the well-known moments accountant. Our experiments demonstrate that in-distribution samples in …
We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy loss bounds. We adapt the Bayesian privacy accounting method to the federated setting and suggest multiple improvements for more efficient privacy budgeting at different levels. Our experiments show significant advantage over the state-of-the-art differential privacy bounds for federated learning on image classification tasks, including a medical application, …
Tsinghua University（清华大学）；Xi’an Jiaotong University（西安交通大学）；Michigan State University（密歇根州立大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；Weill Cornell Medical College（威尔康奈尔医学院）
Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together. In contrast, in single-task learning (STL) each individual task is learned independently. MTL often leads to better trained models because they can leverage the commonalities among related tasks. However, because MTL algorithms can ``leak" information from different models across different tasks, MTL poses a potential security risk. Specifically, an adversary may participate in the MTL process through one task and thereby acquire the model information for another task. The previously proposed privacy-…
University of Texas (UT) at Austin（德克萨斯大学奥斯汀分校）；University of Sao Paulo (USP)（圣保罗大学）
This paper introduces a privacy-aware Bayesian approach that combines ensembles of classifiers and clusterers to perform semi-supervised and transductive learning. We consider scenarios where instances and their classification/clustering results are distributed across different data sites and have sharing restrictions. As a special case, the privacy aware computation of the model when instances of the target data are distributed across different data sites, is also discussed. Experimental results show that the proposed approach can provide good classification accuracies while adhering to the d…
Bayesian neural network (BNN) allows for uncertainty quantification in prediction, offering an advantage over regular neural networks that has not been explored in the differential privacy (DP) framework. We fill this important gap by leveraging recent development in Bayesian deep learning and privacy accounting to offer a more precise analysis of the trade-off between privacy and accuracy in BNN. We propose three DP-BNNs that characterize the weight uncertainty for the same network architecture in distinct ways, namely DP-SGLD (via the noisy gradient method), DP-BBP (via changing the paramete…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Intersectionality is a framework that analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including race, gender, sexual orientation, class, and disability. Intersectionality theory therefore implies it is important that fairness in artificial intelligence systems be protected with regard to multi-dimensional protected attributes. However, the measurement of fairness becomes statistically challenging in the multi-dimensional setting due to data sparsity, which increases rapidly in the number of dimensions, and in the values per dimension. W…
We consider the problem of Bayesian learning on sensitive datasets and present two simple but somewhat surprising results that connect Bayesian learning to "differential privacy:, a cryptographic approach to protect individual-level privacy while permiting database-level utility. Specifically, we show that that under standard assumptions, getting one single sample from a posterior distribution is differentially private "for free". We will see that estimator is statistically consistent, near optimal and computationally tractable whenever the Bayesian model of interest is consistent, optimal and…
The University of Melbourne（墨尔本大学）；Univ-Lille-3（里尔第三大学）；Chalmers University of Technology（查尔姆斯理工大学）
We study how to communicate findings of Bayesian inference to third parties, while preserving the strong guarantee of differential privacy. Our main contributions are four different algorithms for private Bayesian inference on proba-bilistic graphical models. These include two mechanisms for adding noise to the Bayesian updates, either directly to the posterior parameters, or to their Fourier transform so as to preserve update consistency. We also utilise a recently introduced posterior sampling mechanism, for which we prove bounds for the specific but general case of discrete Bayesian network…
School of Management Engineering, Ulsan National Institute of Science and Technology (UNIST)（蔚山科学技术院管理工程学院）
In clinical research, the lack of events of interest often necessitates imbalanced learning. One approach to resolve this obstacle is data integration or sharing, but due to privacy concerns neither is practical. Therefore, there is an increasing demand for a platform on which an analysis can be performed in a federated environment while maintaining privacy. However, it is quite challenging to develop a federated learning algorithm that can address both privacy-preserving and class imbalanced issues. In this study, we introduce a federated generative model learning platform for generating samp…
Aalto University（阿尔托大学）；University of Manchester（曼彻斯特大学）；University of Helsinki（赫尔辛基大学）
In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy. LDP provides client-side privacy by adding noise at the user's end. Thus, clients need not rely on the trustworthiness of the aggregator. In this work, we provide a noise-aware probabilistic modeling framework, which allows Bayesian inference to take into account the noise added for privacy under LDP, conditioned on locally perturbed observations. Stronger privacy protection (compared to the central model) pro…
University of Lille（里尔大学）；Harvard University（哈佛大学）；Chalmers University of Technology（查尔姆斯理工大学）；Google, Inc.（谷歌公司）；The University of Melbourne（墨尔本大学）
Differential privacy formalises privacy-preserving mechanisms that provide access to a database. We pose the question of whether Bayesian inference itself can be used directly to provide private access to data, with no modification. The answer is affirmative: under certain conditions on the prior, sampling from the posterior distribution can be used to achieve a desired level of privacy and utility. To do so, we generalise differential privacy to arbitrary dataset metrics, outcome spaces and distribution families. This allows us to also deal with non-i.i.d or non-tabular datasets. We prove bou…
UC San Diego（加州大学圣地亚哥分校）；University of Amsterdam（阿姆斯特丹大学）
Bayesian inference has great promise for the privacy-preserving analysis of sensitive data, as posterior sampling automatically preserves differential privacy, an algorithmic notion of data privacy, under certain conditions (Dimitrakakis et al., 2014; Wang et al., 2015). While this one posterior sample (OPS) approach elegantly provides privacy "for free," it is data inefficient in the sense of asymptotic relative efficiency (ARE). We show that a simple alternative based on the Laplace mechanism, the workhorse of differential privacy, is as asymptotically efficient as non-private posterior infe…
WeBank（微众银行）；Hong Kong University of Science and Technology（香港科技大学）；Shanghai Jiao Tong University（上海交通大学）
Federated learning (FL) aims to protect data privacy by cooperatively learning a model without sharing private data among users. For Federated Learning of Deep Neural Network with billions of model parameters, existing privacy-preserving solutions are unsatisfactory. Homomorphic encryption (HE) based methods provide secure privacy protections but suffer from extremely high computational and communication overheads rendering it almost useless in practice . Deep learning with Differential Privacy (DP) was implemented as a practical learning algorithm at a manageable cost in complexity. However, …
Linear regression is an important tool across many fields that work with sensitive human-sourced data. Significant prior work has focused on producing differentially private point estimates, which provide a privacy guarantee to individuals while still allowing modelers to draw insights from data by estimating regression coefficients. We investigate the problem of Bayesian linear regression, with the goal of computing posterior distributions that correctly quantify uncertainty given privately released statistics. We show that a naive approach that ignores the noise injected by the privacy mecha…
Differentially Private Online Bayesian Estimation With Adaptive Truncation
Sabancı University（萨班哲大学）；Faculty of Engineering and Natural Sciences, Sabancı University（萨班哲大学工程与自然科学学院）；Center of Excellence in Data Analytics (VERİM), Sabancı University（萨班哲大学数据分析卓越中心（VERİM））
Emory University（埃默里大学）；University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Hong Kong（香港大学）；Sun Yat-sen University（中山大学）；Lehigh University（理海大学）
Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes). Since relational data are often sensitive, we aim to seek effective approaches to generate utility-preserved yet privacy-protected structured data. In this paper, we leverage the differential privacy (DP) framework to formulate and enforce rigorous privacy constraints on deep graph generation models, with a focus on edge-DP to guarantee individual link privacy. In particular, we enforce edge-DP by injecting proper noise to the gradients of a link reco…
The success of applications for sharing GPS trajectories raises serious privacy concerns, in particular about users' home addresses. In this paper we show that a Bayesian approach is natural and effective for a rigorous analysis of home-identification attacks and their countermeasures, in terms of privacy. We focus on a family of countermeasures named "privacy-region strategies", consisting in publishing each trajectory from the first exit to the last entrance from/into a privacy region. Their performance is studied through simulations on Brownian motions.
Federated analytics has many applications in edge computing, its use can lead to better decision making for service provision, product development, and user experience. We propose a Bayesian approach to trend detection in which the probability of a keyword being trendy, given a dataset, is computed via Bayes' Theorem; the probability of a dataset, given that a keyword is trendy, is computed through secure aggregation of such conditional probabilities over local datasets of users. We propose a protocol, named SAFE, for Bayesian federated analytics that offers sufficient privacy for production g…
Duke University（杜克大学）；University at Buffalo, SUNY（纽约州立大学布法罗分校）；Nanjing University（南京大学）
Significant success has been realized recently on applying machine learning to real-world applications. There have also been corresponding concerns on the privacy of training data, which relates to data security and confidentiality issues. Differential privacy provides a principled and rigorous privacy guarantee on machine learning models. While it is common to design a model satisfying a required differential-privacy property by injecting noise, it is generally hard to balance the trade-off between privacy and utility. We show that stochastic gradient Markov chain Monte Carlo (SG-MCMC) -- a c…
Institute for Clarity in Documentation（文档清晰性研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗克库尔中心）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
Federated learning platforms are gaining popularity. One of the major benefits is to mitigate the privacy risks as the learning of algorithms can be achieved without collecting or sharing data. While federated learning (i.e., many based on stochastic gradient algorithms) has shown great promise, there are still many challenging problems in protecting privacy, especially during the process of gradients update and exchange. This paper presents the first gradient-free federated learning framework called GRAFFL for learning a Bayesian generative model based on approximate Bayesian computation. Unl…
Data integration and sharing maximally enhance the potential for novel and meaningful discoveries. However, it is a non-trivial task as integrating data from multiple sources can put sensitive information of study participants at risk. To address the privacy concern, we present a distributed Bayesian learning approach via Preconditioned Stochastic Gradient Langevin Dynamics with RMSprop, which combines differential privacy and homomorphic encryption in a harmonious manner while protecting private information. We applied the proposed secure and privacy-preserving distributed Bayesian learning a…
National University of Singapore（新加坡国立大学）；MIT（麻省理工学院）
Bayesian optimization (BO) has recently been extended to the federated learning (FL) setting by the federated Thompson sampling (FTS) algorithm, which has promising applications such as federated hyperparameter tuning. However, FTS is not equipped with a rigorous privacy guarantee which is an important consideration in FL. Recent works have incorporated differential privacy (DP) into the training of deep neural networks through a general framework for adding DP to iterative algorithms. Following this general DP framework, our work here integrates DP into FTS to preserve user-level privacy. We …
Aalto University（阿尔托大学）；University of Helsinki（赫尔辛基大学）；University of Manchester（曼彻斯特大学）
Generalized linear models (GLMs) such as logistic regression are among the most widely used arms in data analyst's repertoire and often used on sensitive datasets. A large body of prior works that investigate GLMs under differential privacy (DP) constraints provide only private point estimates of the regression coefficients, and are not able to quantify parameter uncertainty. In this work, with logistic and Poisson regression as running examples, we introduce a generic noise-aware DP Bayesian inference method for a GLM at hand, given a noisy sum of summary statistics. Quantifying uncertainty a…
CYBERCAT (Center for Cybersecurity Research of Catalonia)（加泰罗尼亚网络安全研究中心）；ComSCIAM-Center for Computational Science and Applied Mathematics（计算科学与应用数学中心）；Department of Computer Engineering and Mathematics, Universitat Rovira i Virgili（罗维拉-维尔吉利大学计算机工程与数学系）
Microsoft Research（微软研究院）；Microsoft（微软公司）；University College London（伦敦大学学院）
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they afford in practice. An emerging strand of work empirically estimates the protection afforded by differentially private training as a confidence interval for the privacy budget $\varepsilon$ spent on training a model. Existing approaches derive confidence intervals for $\varepsilon$ from confidence intervals for the false positive and false negative rates of me…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Microsoft Research（微软研究院）；Cornell University（康奈尔大学）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
We present a general method for privacy-preserving Bayesian inference in Poisson factorization, a broad class of models that includes some of the most widely used models in the social sciences. Our method satisfies limited precision local privacy, a generalization of local differential privacy, which we introduce to formulate privacy guarantees appropriate for sparse count data. We develop an MCMC algorithm that approximates the locally private posterior over model parameters given data that has been locally privatized by the geometric mechanism (Ghosh et al., 2012). Our solution is based on t…
Bayesian learning via Stochastic Gradient Langevin Dynamics (SGLD) has been suggested for differentially private learning. While previous research provides differential privacy bounds for SGLD at the initial steps of the algorithm or when close to convergence, the question of what differential privacy guarantees can be made in between remains unanswered. This interim region is of great importance, especially for Bayesian neural networks, as it is hard to guarantee convergence to the posterior. This paper shows that using SGLD might result in unbounded privacy loss for this interim region, even…
Northeastern University（东北大学）；University of Pennsylvania（宾夕法尼亚大学）
Motivated by settings in which predictive models may be required to be non-discriminatory with respect to certain attributes (such as race), but even collecting the sensitive attribute may be forbidden or restricted, we initiate the study of fair learning under the constraint of differential privacy. We design two learning algorithms that simultaneously promise differential privacy and equalized odds, a 'fairness' condition that corresponds to equalizing false positive and negative rates across protected groups. Our first algorithm is a private implementation of the equalized odds post-process…
In statistical learning, a dataset is often partitioned into two parts: the training set and the holdout (i.e., testing) set. For instance, the training set is used to learn a predictor, and then the holdout set is used for estimating the accuracy of the predictor on the true distribution. However, often in practice, the holdout dataset is reused and the estimates tested on the holdout dataset are chosen adaptively based on the results of prior estimates, leading to that the predictor may become dependent of the holdout set. Hence, overfitting may occur, and the learned models may not generali…
The large number of publicly available survey datasets of wide variety, albeit useful, raise respondent-level privacy concerns. The synthetic data approach to data privacy and confidentiality has been shown useful in terms of privacy protection and utility preservation. This paper aims at illustrating how synthetic data can facilitate the dissemination of highly sensitive information about youth risk behavior by presenting a case study of synthetic data for a sample of the Youth Risk Behavior Survey (YRBS). Given the categorical nature of almost all variables in YRBS, the Dirichlet Process mix…
DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents
Sangmyung University（祥明大学）；College of Staten Island, The City University of New York（纽约城市大学斯塔滕岛学院）；Sookmyung Women’s University（淑明女子大学）；Hansung University（汉城大学）；Yonsei University（延世大学）
Distributed data analysis without revealing the individual data has recently attracted significant attention in several applications. A collaborative data analysis through sharing dimensionality reduced representations of data has been proposed as a non-model sharing-type federated learning. This paper analyzes the accuracy and privacy evaluations of this novel framework. In the accuracy analysis, we provided sufficient conditions for the equivalence of the collaborative data analysis and the centralized analysis with dimensionality reduction. In the privacy analysis, we proved that collaborat…
Statistical agencies utilize models to synthesize respondent-level data for release to the public for privacy protection. In this work, we efficiently induce privacy protection into any Bayesian synthesis model by employing a pseudo likelihood that exponentiates each likelihood contribution by an observation record-indexed weight in [0, 1], defined to be inversely proportional to the identification risk for that record. We start with the marginal probability of identification risk for a record, which is composed as the probability that the identity of the record may be disclosed. Our applicati…
When performing Bayesian computations in practice, one is often faced with the challenge that the constituent model components and/or the data are only available in a distributed fashion, e.g. due to privacy concerns or sheer volume. While various methods have been proposed for performing posterior inference in such federated settings, these either make very strong assumptions on the data and/or model or otherwise introduce significant bias when the local posteriors are combined to form an approximation of the target posterior. By leveraging recently developed methods for Markov Chain Monte Ca…
Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation
Department of Mathematics and Computer Science University of Southern Denmark（丹麦南部大学数学与计算机科学系）；Department of Mathematics and Computer Science Freie Universität Berlin（柏林自由大学数学与计算机科学系）；Faculty for Informatik Universität der Bundeswehr München（联邦国防军大学慕尼黑信息学院）
Differentially private mechanisms protect privacy by introducing additional randomness into the data. Restricting access to only the privatized data makes it challenging to perform valid statistical inference on parameters underlying the confidential data. Specifically, the likelihood function of the privatized data requires integrating over the large space of confidential databases and is typically intractable. For Bayesian analysis, this results in a posterior distribution that is doubly intractable, rendering traditional MCMC techniques inapplicable. We propose an MCMC framework to perform …
Statistical agencies utilize models to synthesize respondent-level data for release to the general public as an alternative to the actual data records. A Bayesian model synthesizer encodes privacy protection by employing a hierarchical prior construction that induces smoothing of the real data distribution. Synthetic respondent-level data records are often preferred to summary data tables due to the many possible uses by researchers and data analysts. Agencies balance a trade-off between utility of the synthetic data versus disclosure risks and hold a specific target threshold for disclosure r…
