Preserving the privacy of individual databases when carrying out statistical calculations has a long history in statistics and had been the focus of much recent attention in machine learning In this paper, we present a protocol for computing logistic regression when the data are held by separate parties without actually combining information sources by exploiting results from the literature on multi-party secure computation. We provide only the final result of the calculation compared with other methods that share intermediate values and thus present an opportunity for compromise of values in the combined database. Our paper has two themes: (1) the development of a secure protocol for computing the logistic parameters, and a demonstration of its performances in practice, and (2) and amended protocol that speeds up the computation of the logistic function. We illustrate the nature of the calculations and their accuracy using an extract of data from the Current Population Survey divided between two parties.
Recent work has shown that cell phone mobility data has the unique potential to create accurate models for human mobility and consequently the spread of infected diseases. While prior studies have exclusively relied on a mobile network operator's subscribers' aggregated data in modelling disease dynamics, it may be preferable to contemplate aggregated mobility data of infected individuals only. Clearly, naively linking mobile phone data with health records would violate privacy by either allowing to track mobility patterns of infected individuals, leak information on who is infected, or both. …
With the rapid development of GPS enabled devices (smartphones) and location-based applications, location privacy is increasingly concerned. Intuitively, it is widely believed that location privacy can be preserved by publishing aggregated mobility data, such as the number of users in an area at some time. However, a recent attack shows that these aggregated mobility data can be exploited to recover individual trajectories. In this paper, we first propose two differentially private basic schemes for aggregated mobility data publication, namely direct perturbation and threshold perturbation, wh…
Planning is one of the main approaches used to improve agents' working efficiency by making plans beforehand. However, during planning, agents face the risk of having their private information leaked. This paper proposes a novel strong privacy-preserving planning approach for logistic-like problems. This approach outperforms existing approaches by addressing two challenges: 1) simultaneously achieving strong privacy, completeness and efficiency, and 2) addressing communication constraints. These two challenges are prevalent in many real-world applications including logistics in military enviro…
Inria（法国国家信息与自动化研究所）；École Polytechnique (IPP)（巴黎综合理工学院（巴黎理工学院））；Femto-ST Institute（弗朗什-孔泰电子、力学、热学与光学科学技术研究所）；Univ. Bourg. Franche-Comté（勃艮第-弗朗什-孔泰大学）；UBFC（勃艮第-弗朗什-孔泰大学联盟）；CNRS（法国国家科学研究中心）；Orange Applications For Business（Orange商业应用公司）；Orange Labs.（奥兰治实验室）；Antonine University Hadat-Baabda（哈达特-巴卜达安东尼大学）；National University of Singapore（新加坡国立大学）
This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy guarantee in two different and independent steps when training deep learning models. On one hand, we considered \textit{gradient perturbation}, which uses the differentially private stochastic gradient descent algorithm to guarantee the privacy of each time series sample in the learning stage. On the other hand, we considered \textit{input perturbation}, which add…
This paper presents a new privacy-preserving smart metering system. Our scheme is private under the differential privacy model and therefore provides strong and provable guarantees. With our scheme, an (electricity) supplier can periodically collect data from smart meters and derive aggregated statistics while learning only limited information about the activities of individual households. For example, a supplier cannot tell from a user's trace when he watched TV or turned on heating. Our scheme is simple, efficient and practical. Processing cost is very limited: smart meters only have to add …
We consider the problem of privately releasing aggregated network statistics obtained from solving a DC optimal power flow (OPF) problem. It is shown that the mechanism that determines the noise distribution parameters are linked to the topology of the power system and the monotonicity of the network. We derive a measure of "almost" monotonicity and show how it can be used in conjunction with a linear program in order to release aggregated OPF data using the differential privacy framework.
Beijing Key Laboratory of Information Service Engineering, Beijing Union University（北京联合大学信息服务业工程北京市重点实验室）；Vanderbilt University（范德堡大学）
As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on. These domains often involve data of human subjects that are contingent upon strict privacy regulations. Increasing concerns over data privacy make it more and more difficult to coordinate and conduct large-scale collaborative studies, which typically rely on cross-institution data sharing and joint analysis. Our work here focuses on safeguarding regularized logistic regression, a widely-used machi…
University of Maryland（马里兰大学）；New York University（纽约大学）
Federated learning has quickly gained popularity with its promises of increased user privacy and efficiency. Previous works have shown that federated gradient updates contain information that can be used to approximately recover user data in some situations. These previous attacks on user privacy have been limited in scope and do not scale to gradient updates aggregated over even a handful of data points, leaving some to conclude that data privacy is still intact for realistic training regimes. In this work, we introduce a new threat model based on minimal but malicious modifications of the sh…
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…
Tencent Medical AI Lab（腾讯医疗人工智能实验室）；Georgia State University（佐治亚州立大学）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；State University of New York at Buffalo（纽约州立大学布法罗分校）；Alibaba Group（阿里巴巴集团）
Nowadays, crowd sensing becomes increasingly more popular due to the ubiquitous usage of mobile devices. However, the quality of such human-generated sensory data varies significantly among different users. To better utilize sensory data, the problem of truth discovery, whose goal is to estimate user quality and infer reliable aggregated results through quality-aware data aggregation, has emerged as a hot topic. Although the existing truth discovery approaches can provide reliable aggregated results, they fail to protect the private information of individual users. Moreover, crowd sensing syst…
Leveraging transfer learning has recently been shown to be an effective strategy for training large models with Differential Privacy (DP). Moreover, somewhat surprisingly, recent works have found that privately training just the last layer of a pre-trained model provides the best utility with DP. While past studies largely rely on algorithms like DP-SGD for training large models, in the specific case of privately learning from features, we observe that computational burden is low enough to allow for more sophisticated optimization schemes, including second-order methods. To that end, we system…
Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning
The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）；School of Cyber Science and Technology, Zhejiang University（浙江大学网络空间安全学院）；College of Computer Science and Technology, Taiyuan University of Technology（太原理工大学计算机科学与技术学院）
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…
Highly accurate profiles of consumers daily energy usage are reported to power grid via smart meters which enables smart grid to effectively regulate power demand and supply. However, consumers energy consumption pattern can reveal personal and sensitive information regarding their lifestyle. Therefore, to ensure users privacy, differentially distributed noise is added to the original data. This technique comes with a trade off between privacy of the consumer versus utility of the data in terms of providing services like billing, Demand Response schemes, and Load Monitoring. In this paper, we …
Criteo AI Lab（Criteo AI实验室）；Meta Platforms, Inc.（Meta平台公司）；Criteo AI Lab and Hui Yang Affiliation: Meta Platforms, Inc.（Criteo AI实验室）
Designing data sharing mechanisms providing performance and strong privacy guarantees is a hot topic for the Online Advertising industry. Namely, a prominent proposal discussed under the Improving Web Advertising Business Group at W3C only allows sharing advertising signals through aggregated, differentially private reports of past displays. To study this proposal extensively, an open Privacy-Preserving Machine Learning Challenge took place at AdKDD'21, a premier workshop on Advertising Science with data provided by advertising company Criteo. In this paper, we describe the challenge tasks, th…
Local differential privacy (LDP) can provide each user with strong privacy guarantees under untrusted data curators while ensuring accurate statistics derived from privatized data. Due to its powerfulness, LDP has been widely adopted to protect privacy in various tasks (e.g., heavy hitters discovery, probability estimation) and systems (e.g., Google Chrome, Apple iOS). Although $ε$-LDP has been proposed for many years, the more general notion of $(ε, δ)$-LDP has only been studied in very few papers, which mainly consider mean estimation for numeric data. Besides, prior solutions achieve $(ε, δ…
Columbia University（哥伦比亚大学）；NTUA（雅典国立技术大学）；Northeastern University（东北大学）
We provide computationally efficient, differentially private algorithms for the classical regression settings of Least Squares Fitting, Binary Regression and Linear Regression with unbounded covariates. Prior to our work, privacy constraints in such regression settings were studied under strong a priori bounds on covariates. We consider the case of Gaussian marginals and extend recent differentially private techniques on mean and covariance estimation (Kamath et al., 2019; Karwa and Vadhan, 2018) to the sub-gaussian regime. We provide a novel technical analysis yielding differentially private …
Booz Allen Hamilton（博思艾伦汉密尔顿公司）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Air Force Research Laboratory（美国空军研究实验室）
We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or membership inference, they have been tailored to specific models or have demonstrated low statistical power. Our work develops a general methodology to empirically evaluate the privacy of differentially private machine learning implementations, combining improved privacy search and verification methods with a toolkit of influence-based poisoning attacks. We demonst…
In tracing the (robotically automated) logistics of large quantities of goods, inexpensive passive RFID tags are preferred for cost reasons. Accordingly, security between such tags and readers have primarily been studied among many issues of RFID. However, the authenticity of data cannot be guaranteed if logistics services can give false information. Although the use of blockchain is often discussed, it is simply a recording system, so there is a risk that false records may be written to it. As a solution, we propose a design in which a digitally signing, location-constrained and tamper-eviden…
Hazy（Hazy公司）；University of Edinburgh（爱丁堡大学）；University College London（伦敦大学学院）
We propose a general, flexible, and scalable framework dpart, an open source Python library for differentially private synthetic data generation. Central to the approach is autoregressive modelling -- breaking the joint data distribution to a sequence of lower-dimensional conditional distributions, captured by various methods such as machine learning models (logistic/linear regression, decision trees, etc.), simple histogram counts, or custom techniques. The library has been created with a view to serve as a quick and accessible baseline as well as to accommodate a wide audience of users, from…
Private data generated by edge devices -- from smart phones to automotive electronics -- are highly informative when aggregated but can be damaging when mishandled. A variety of solutions are being explored but have not yet won the public's trust and full backing of mobile platforms. In this work, we propose numerical aggregation protocols that empirically improve upon prior art, while providing comparable local differential privacy guarantees. Sharing a single private bit per value supports privacy metering that enable privacy controls and guarantees that are not covered by differential priva…
Georgia Institute of Technology（佐治亚理工学院）；Meta AI；Pennsylvania State University（宾夕法尼亚州立大学）；Virginia Tech（弗吉尼亚理工大学）；Cornell University（康奈尔大学）
Federated learning (FL) aims to perform privacy-preserving machine learning on distributed data held by multiple data owners. To this end, FL requires the data owners to perform training locally and share the gradient updates (instead of the private inputs) with the central server, which are then securely aggregated over multiple data owners. Although aggregation by itself does not provably offer privacy protection, prior work showed that it may suffice if the batch size is sufficiently large. In this paper, we propose the Cocktail Party Attack (CPA) that, contrary to prior belief, is able to …
In this paper, we present Talaria, a novel permissioned blockchain simulator that supports numerous protocols and use cases, most notably in supply chain management. Talaria extends the capability of BlockSim, an existing blockchain simulator, to include permissioned blockchains and serves as a foundation for further private blockchain assessment. Talaria is designed with both practical Byzantine Fault Tolerance (pBFT) and simplified version of Proof-of-Authority consensus protocols, but can be revised to include other permissioned protocols within its modular framework. Moreover, Talaria is a…
This paper proposes a framework to investigate the value of sharing privacy-protected smart meter data between domestic consumers and load serving entities. The framework consists of a discounted differential privacy model to ensure individuals cannot be identified from aggregated data, a ANN-based short-term load forecasting to quantify the impact of data availability and privacy protection on the forecasting error and an optimal procurement problem in day-ahead and balancing markets to assess the market value of the privacy-utility trade-off. The framework demonstrates that when the load pro…
Nagoya Institute of Technology（名古屋工业大学）；Mie University（三重大学）；University of Tsukuba（筑波大学）
Privacy concern has been increasingly important in many machine learning (ML) problems. We study empirical risk minimization (ERM) problems under secure multi-party computation (MPC) frameworks. Main technical tools for MPC have been developed based on cryptography. One of limitations in current cryptographically private ML is that it is computationally intractable to evaluate non-linear functions such as logarithmic functions or exponential functions. Therefore, for a class of ERM problems such as logistic regression in which non-linear function evaluations are required, one can only obtain a…
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties. It is renowned for preserving privacy as the data never leaves the computational devices, and recent approaches further enhance its privacy by hiding messages transferred in encryption. However, we found that despite the efforts, federated learning remains privacy-threatening, due to its interactive nature across different parties. In this paper, we analyze the privacy threats in industrial-level federated learning frameworks with secure computation, and reveal such threats…
Cornell University（康奈尔大学）；Stanford University（斯坦福大学）；Indian Institute of Science（印度科学学院）
We study the problem of distribution testing when the samples can only be accessed using a locally differentially private mechanism and focus on two representative testing questions of identity (goodness-of-fit) and independence testing for discrete distributions. We are concerned with two settings: First, when we insist on using an already deployed, general-purpose locally differentially private mechanism such as the popular RAPPOR or the recently introduced Hadamard Response for collecting data, and must build our tests based on the data collected via this mechanism; and second, when no such…
University of British Columbia（不列颠哥伦比亚大学）；University of Toronto（多伦多大学）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）
Distributed machine learning (ML) systems today use an unsophisticated threat model: data sources must trust a central ML process. We propose a brokered learning abstraction that allows data sources to contribute towards a globally-shared model with provable privacy guarantees in an untrusted setting. We realize this abstraction by building on federated learning, the state of the art in multi-party ML, to construct TorMentor: an anonymous hidden service that supports private multi-party ML. We define a new threat model by characterizing, developing and evaluating new attacks in the brokered le…
University of Southern California（南加州大学）；University of California, Riverside（加州大学河滨分校）
How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed workers. We characterize CodedPrivateML's privacy threshold and prove its convergence for logistic (and linear) regression. Furthermore, via extensive experiments on Amazon EC2, we demonstrate that CodedPrivateML provides significant speedup over cryptographic approaches based on …
We consider machine learning, particularly regression, using locally-differentially private datasets. The Wasserstein distance is used to define an ambiguity set centered at the empirical distribution of the dataset corrupted by local differential privacy noise. The ambiguity set is shown to contain the probability distribution of unperturbed, clean data. The radius of the ambiguity set is a function of the privacy budget, spread of the data, and the size of the problem. Hence, machine learning with locally-differentially private datasets can be rewritten as a distributionally-robust optimizat…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；The Chinese University of Hong Kong（香港中文大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Northwestern University（西北大学）
Machine learning benefits from large training datasets, which may not always be possible to collect by any single entity, especially when using privacy-sensitive data. In many contexts, such as healthcare and finance, separate parties may wish to collaborate and learn from each other's data but are prevented from doing so due to privacy regulations. Some regulations prevent explicit sharing of data between parties by joining datasets in a central location (confidentiality). Others also limit implicit sharing of data, e.g., through model predictions (privacy). There is currently no method that …
Histograms and synthetic data are of key importance in data analysis. However, researchers have shown that even aggregated data such as histograms, containing no obvious sensitive attributes, can result in privacy leakage. To enable data analysis, a strong notion of privacy is required to avoid risking unintended privacy violations. Such a strong notion of privacy is differential privacy, a statistical notion of privacy that makes privacy leakage quantifiable. The caveat regarding differential privacy is that while it has strong guarantees for privacy, privacy comes at a cost of accuracy. Desp…
Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol. However, this process assumes a trusted centralized infrastructure for coordination, and clients must trust that the central service does not use the byproducts of client data. In addition to this, a group of malicious clients could also harm the performance of the model by carrying out a poisoning attack. As a response, we propose Biscotti: a fully decentralized peer to peer (P…
Georgia Institute of Technology（佐治亚理工学院）；J.P. Morgan AI Research（摩根大通人工智能研究院）
Federated Learning enables a population of clients, working with a trusted server, to collaboratively learn a shared machine learning model while keeping each client's data within its own local systems. This reduces the risk of exposing sensitive data, but it is still possible to reverse engineer information about a client's private data set from communicated model parameters. Most federated learning systems therefore use differential privacy to introduce noise to the parameters. This adds uncertainty to any attempt to reveal private client data, but also reduces the accuracy of the shared mod…
Many applications of Bayesian data analysis involve sensitive information, motivating methods which ensure that privacy is protected. We introduce a general privacy-preserving framework for Variational Bayes (VB), a widely used optimization-based Bayesian inference method. Our framework respects differential privacy, the gold-standard privacy criterion, and encompasses a large class of probabilistic models, called the Conjugate Exponential (CE) family. We observe that we can straightforwardly privatise VB's approximate posterior distributions for models in the CE family, by perturbing the expe…
Traditional statistical methods for confidentiality protection of statistical databases do not scale well to deal with GWAS (genome-wide association studies) databases especially in terms of guarantees regarding protection from linkage to external information. The more recent concept of differential privacy, introduced by the cryptographic community, is an approach which provides a rigorous definition of privacy with meaningful privacy guarantees in the presence of arbitrary external information, although the guarantees come at a serious price in terms of data utility. Building on such notions…
University of California, San Diego（加州大学圣地亚哥分校）；Columbia University（哥伦比亚大学）
Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the $ε$-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving machin…
