In this paper, we present a general multiparty modeling paradigm with Privacy Preserving Principal Component Analysis (PPPCA) for horizontally partitioned data. PPPCA can accomplish multiparty cooperative execution of PCA under the premise of keeping plaintext data locally. We also propose implementations using two techniques, i.e., homomorphic encryption and secret sharing. The output of PPPCA can be sent directly to data consumer to build any machine learning models. We conduct experiments on three UCI benchmark datasets and a real-world fraud detection dataset. Results show that the accuracy of the model built upon PPPCA is the same as the model with PCA that is built based on centralized plaintext data.
Improved Privacy-Preserving PCA Using Optimized Homomorphic Matrix Multiplication
School of Software, Shandong University（山东大学软件学院）；Zhejiang Lab（之江实验室）；Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR)（山东大学-南洋理工大学人工智能联合研究中心（C-FAIR））
The exponential mechanism is a fundamental tool of Differential Privacy (DP) due to its strong privacy guarantees and flexibility. We study its extension to settings with summaries based on infinite dimensional outputs such as with functional data analysis, shape analysis, and nonparametric statistics. We show that one can design the mechanism with respect to a specific base measure over the output space, such as a Guassian process. We provide a positive result that establishes a Central Limit Theorem for the exponential mechanism quite broadly. We also provide an apparent negative result, sho…
Federated learning (FL) is a privacy-aware data mining strategy keeping the private data on the owners' machine and thereby confidential. The clients compute local models and send them to an aggregator which computes a global model. In hybrid FL, the local parameters are additionally masked using secure aggregation, such that only the global aggregated statistics become available in clear text, not the client specific updates. Federated QR decomposition has not been studied extensively in the context of cross-silo federated learning. In this article, we investigate the suitability of three QR …
University of Campinas（坎皮纳斯大学）；University of Washington Tacoma（华盛顿大学塔科马分校）；Monash University（莫纳什大学）；Aarhus University（奥胡斯大学）
We propose a privacy-preserving Naive Bayes classifier and apply it to the problem of private text classification. In this setting, a party (Alice) holds a text message, while another party (Bob) holds a classifier. At the end of the protocol, Alice will only learn the result of the classifier applied to her text input and Bob learns nothing. Our solution is based on Secure Multiparty Computation (SMC). Our Rust implementation provides a fast and secure solution for the classification of unstructured text. Applying our solution to the case of spam detection (the solution is generic, and can be…
Hong Kong University of Science and Technology（香港科技大学）；University of Warwick（华威大学）
We study the fundamental problem of frequency estimation under both privacy and communication constraints, where the data is distributed among $k$ parties. We consider two application scenarios: (1) one-shot, where the data is static and the aggregator conducts a one-time computation; and (2) streaming, where each party receives a stream of items over time and the aggregator continuously monitors the frequencies. We adopt the model of multiparty differential privacy (MDP), which is more general than local differential privacy (LDP) and (centralized) differential privacy. Our protocols achieve …
University of Washington（华盛顿大学）；Monash University（莫纳什大学）；Ghent University（根特大学）
Existing work on privacy-preserving machine learning with Secure Multiparty Computation (MPC) is almost exclusively focused on model training and on inference with trained models, thereby overlooking the important data pre-processing stage. In this work, we propose the first MPC based protocol for private feature selection based on the filter method, which is independent of model training, and can be used in combination with any MPC protocol to rank features. We propose an efficient feature scoring protocol based on Gini impurity to this end. To demonstrate the feasibility of our approach for …
Centralized systems in the Internet of Things---be it local middleware or cloud-based services---fail to fundamentally address privacy of the collected data. We propose an architecture featuring secure multiparty computation at its core in order to realize data processing systems which already incorporate support for privacy protection in the architecture.
Identifying anomaly multimedia traffic in cyberspace is a big challenge in distributed service systems, multiple generation networks and future internet of everything. This letter explores meta-generalization for a multiparty privacy learning model in graynet to improve the performance of anomaly multimedia traffic identification. The multiparty privacy learning model in graynet is a globally shared model that is partitioned, distributed and trained by exchanging multiparty parameters updates with preserving private data. The meta-generalization refers to discovering the inherent attributes of…
Training Differentially Private Models with Secure Multiparty Computation
School of Engineering and Technology, University of Washington Tacoma（华盛顿大学塔科马分校工程与技术学院）；University of Brasilia（巴西利亚大学）；Monash University（莫纳什大学）；Ghent University（根特大学）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）
In recent years, machine learning techniques are widely used in numerous applications, such as weather forecast, financial data analysis, spam filtering, and medical prediction. In the meantime, massive data generated from multiple sources further improve the performance of machine learning tools. However, data sharing from multiple sources brings privacy issues for those sources since sensitive information may be leaked in this process. In this paper, we propose a framework enabling multiple parties to collaboratively and accurately train a learning model over distributed datasets while guara…
Privacy-preserving data mining has become an important topic. People have built several multi-party-computation (MPC)-based frameworks to provide theoretically guaranteed privacy, the poor performance of real-world algorithms have always been a challenge. Using Principal Component Analysis (PCA) as an example, we show that by considering the unique performance characters of the MPC platform, we can design highly effective algorithm-level optimizations, such as replacing expensive operators and batching up. We achieve about 200$\times$ performance boost over existing privacy-preserving PCA algo…
We introduce a framework for navigating through cluttered environments by connecting multiple cameras together while simultaneously preserving privacy. Occlusions and obstacles in large environments are often challenging situations for navigation agents because the environment is not fully observable from a single camera view. Given multiple camera views of an environment, our approach learns to produce a multiview scene representation that can only be used for navigation, provably preventing one party from inferring anything beyond the output task. On a new navigation dataset that we will pub…
Decentralized deep learning plays a key role in collaborative model training due to its attractive properties, including tolerating high network latency and less prone to single-point failures. Unfortunately, such a training mode is more vulnerable to data privacy leaks compared to other distributed training frameworks. Existing efforts exclusively use differential privacy as the cornerstone to alleviate the data privacy threat. However, it is still not clear whether differential privacy can provide a satisfactory utility-privacy trade-off for model training, due to its inherent contradictions…
The ongoing transition from a linear (produce-use-dispose) to a circular economy poses significant challenges to current state-of-the-art information and communication technologies. In particular, the derivation of integrated, high-level views on material, process, and product streams from (real-time) data produced along value chains is challenging for several reasons. Most importantly, sufficiently rich data is often available yet not shared across company borders because of privacy concerns which make it impossible to build integrated process models that capture the interrelations between in…
We present a solution to the problem of privacy invasion in a multiparty digital rights management scheme. (Roaming) users buy content licenses from a content provider and execute it at any nearby content distributor. Our approach, which does not need any trusted third party--in contrast to most related work on privacy-preserving DRM--is based on a re-encryption scheme that runs on any mobile Android device. Only a minor security-critical part needs to be performed on the device's smartcard which could, for instance, be a SIM card.
Microsoft（微软）；University of Washington Tacoma（华盛顿大学塔科马分校）；Universidade de Brasilia（巴西利亚大学）；Ghent University（根特大学）
Legal and ethical restrictions on accessing relevant data inhibit data science research in critical domains such as health, finance, and education. Synthetic data generation algorithms with privacy guarantees are emerging as a paradigm to break this data logjam. Existing approaches, however, assume that the data holders supply their raw data to a trusted curator, who uses it as fuel for synthetic data generation. This severely limits the applicability, as much of the valuable data in the world is locked up in silos, controlled by entities who cannot show their data to each other or a central a…
How to achieve differential privacy in the distributed setting, where the dataset is distributed among the distrustful parties, is an important problem. We consider in what condition can a protocol inherit the differential privacy property of a function it computes. The heart of the problem is the secure multiparty computation of randomized function. A notion \emph{obliviousness} is introduced, which captures the key security problems when computing a randomized function from a deterministic one in the distributed setting. By this observation, a sufficient and necessary condition about computi…
Sharing and working on sensitive data in distributed settings from healthcare to finance is a major challenge due to security and privacy concerns. Secure multiparty computation (SMC) is a viable panacea for this, allowing distributed parties to make computations while the parties learn nothing about their data, but the final result. Although SMC is instrumental in such distributed settings, it does not provide any guarantees not to leak any information about individuals to adversaries. Differential privacy (DP) can be utilized to address this; however, achieving SMC with DP is not a trivial t…
Credit risk modeling has permeated our everyday life. Most banks and financial companies use this technique to model their clients' trustworthiness. While machine learning is increasingly used in this field, the resulting large-scale collection of user private information has reinvigorated the privacy debate, considering dozens of data breach incidents every year caused by unauthorized hackers, and (potentially even more) information misuse/abuse by authorized parties. To address those critical concerns, this paper proposes a framework of Privacy-preserving Credit risk modeling based on Advers…
In this paper we propose a novel protocol that allows suppliers and grid operators to collect users' aggregate metering data in a secure and privacy-preserving manner. We use secure multiparty computation to ensure privacy protection. In addition, we propose three different data aggregation algorithms that offer different balances between privacy-protection and performance. Our protocol is designed for a realistic scenario in which the data need to be sent to different parties, such as grid operators and suppliers. Furthermore, it facilitates an accurate calculation of transmission, distributi…
In the Internet of Things and smart environments data, collected from distributed sensors, is typically stored and processed by a central middleware. This allows applications to query the data they need for providing further services. However, centralization of data causes several privacy threats: The middleware becomes a third party which has to be trusted, linkage and correlation of data from different context becomes possible and data subject lose control over their data. Hence, other approaches than centralized processing should be considered. Here, Secure Multiparty Computation is a promi…
The precise design of a system may be considered a trade secret which should be protected, whilst at the same time component manufacturers are sometimes reluctant to release full test data (perhaps only providing mean time to failure data). In this situation it seems impractical to both produce an accurate reliability assessment and satisfy all parties' privacy requirements. However, we present recent developments in cryptography which, when combined with the recently developed survival signature in reliability theory, allows almost total privacy to be maintained in a cryptographically strong …
The Ohio State University（俄亥俄州立大学）；University of California, San Diego（加州大学圣地亚哥分校）
Learning a classifier from private data collected by multiple parties is an important problem that has many potential applications. How can we build an accurate and differentially private global classifier by combining locally-trained classifiers from different parties, without access to any party's private data? We propose to transfer the `knowledge' of the local classifier ensemble by first creating labeled data from auxiliary unlabeled data, and then train a global $ε$-differentially private classifier. We show that majority voting is too sensitive and therefore propose a new risk weighted …
Rutgers, The State University of New Jersey（罗格斯新泽西州立大学）
In many signal processing and machine learning applications, datasets containing private information are held at different locations, requiring the development of distributed privacy-preserving algorithms. Tensor and matrix factorizations are key components of many processing pipelines. In the distributed setting, differentially private algorithms suffer because they introduce noise to guarantee privacy. This paper designs new and improved distributed and differentially private algorithms for two popular matrix and tensor factorization methods: principal component analysis (PCA) and orthogonal…
We design a scalable algorithm to privately generate location heatmaps over decentralized data from millions of user devices. It aims to ensure differential privacy before data becomes visible to a service provider while maintaining high data accuracy and minimizing resource consumption on users' devices. To achieve this, we revisit distributed differential privacy based on recent results in secure multiparty computation, and we design a scalable and adaptive distributed differential privacy approach for location analytics. Evaluation on public location datasets shows that this approach succes…
Privacy preserving machine learning is an active area of research usually relying on techniques such as homomorphic encryption or secure multiparty computation. Recent novel encryption techniques for performing machine learning using deep neural nets on images have recently been proposed by Tanaka and Sirichotedumrong, Kinoshita, and Kiya. We present new chosen-plaintext and ciphertext-only attacks against both of these proposed image encryption schemes and demonstrate the attacks' effectiveness on several examples.
Mila – Quebec AI Institute（Mila – 魁北克人工智能研究所）；HEC Montréal（蒙特利尔高等商学院）；University of Washington Tacoma（华盛顿大学塔科马分校）；Ghent University（根特大学）
Group fairness ensures that the outcome of machine learning (ML) based decision making systems are not biased towards a certain group of people defined by a sensitive attribute such as gender or ethnicity. Achieving group fairness in Federated Learning (FL) is challenging because mitigating bias inherently requires using the sensitive attribute values of all clients, while FL is aimed precisely at protecting privacy by not giving access to the clients' data. As we show in this paper, this conflict between fairness and privacy in FL can be resolved by combining FL with Secure Multiparty Computa…
Logic Programming (LP) is a subcategory of declarative programming that is considered to be relatively simple for non-programmers. LP developers focus on describing facts and rules of a logical derivation, and do not need to think about the algorithms actually implementing the derivation. Secure multiparty computation (MPC) is a cryptographic technology that allows to perform computation on private data without actually seeing the data. In this paper, we bring together the notions of MPC and LP, allowing users to write privacy-preserving applications in logic programming language.
Multisite medical data sharing is critical in modern clinical practice and medical research. The challenge is to conduct data sharing that preserves individual privacy and data usability. The shortcomings of traditional privacy-enhancing technologies mean that institutions rely on bespoke data sharing contracts. These contracts increase the inefficiency of data sharing and may disincentivize important clinical treatment and medical research. This paper provides a synthesis between two novel advanced privacy enhancing technologies (PETs): Homomorphic Encryption and Secure Multiparty Computation…
Collaborative learning enables two or more participants, each with their own training dataset, to collaboratively learn a joint model. It is desirable that the collaboration should not cause the disclosure of either the raw datasets of each individual owner or the local model parameters trained on them. This privacy-preservation requirement has been approached through differential privacy mechanisms, homomorphic encryption (HE) and secure multiparty computation (MPC), but existing attempts may either introduce the loss of model accuracy or imply significant computational and/or communicational…
University of Pittsburgh（匹兹堡大学）；IBM Almaden Research Center（IBM阿尔马登研究中心）
Federated learning has emerged as a promising approach for collaborative and privacy-preserving learning. Participants in a federated learning process cooperatively train a model by exchanging model parameters instead of the actual training data, which they might want to keep private. However, parameter interaction and the resulting model still might disclose information about the training data used. To address these privacy concerns, several approaches have been proposed based on differential privacy and secure multiparty computation (SMC), among others. They often result in large communicati…
Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data process, machine learning, deep learning, and federated learning. Although DP has become an active and influential area, it is not the best remedy for all privacy problems in different scenarios. Moreover, there are also some misunderstanding, misuse, and great challenges of DP in specific applications. In this paper, we point out a series of limits and open chal…
Imperial College London（帝国理工学院）；DeepMind（深度思维）；University of Oxford（牛津大学）；Case Western Reserve University（凯斯西储大学）
We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs such as Federated Learning, Secure Multiparty Computation, and Differential Privacy while still exposing a familiar deep learning API to the end-user. We report early results on the Boston Housing and Pima Indian Diabetes datasets. While the privacy features apart from Differenti…
Secure Multiparty Computation (SMC) allows parties to know the result of cooperative computation while preserving privacy of individual data. Secure sum computation is an important application of SMC. In our proposed protocols parties are allowed to compute the sum while keeping their individual data secret with increased computation complexity for hacking individual data. In this paper the data of individual party is broken into a fixed number of segments. For increasing the complexity we have used the randomization technique with segmentation
University of Washington（华盛顿大学）；Google Research（谷歌研究院）
We study the canonical statistical task of computing the principal component from $n$ i.i.d.~data in $d$ dimensions under $(\varepsilon,δ)$-differential privacy. Although extensively studied in literature, existing solutions fall short on two key aspects: ($i$) even for Gaussian data, existing private algorithms require the number of samples $n$ to scale super-linearly with $d$, i.e., $n=Ω(d^{3/2})$, to obtain non-trivial results while non-private PCA requires only $n=O(d)$, and ($ii$) existing techniques suffer from a non-vanishing error even when the randomness in each data point is arbitrar…
Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；University of Washington Tacoma（华盛顿大学塔科马分校）；Ghent University（根特大学）
Machine learning (ML) has become prominent in applications that directly affect people's quality of life, including in healthcare, justice, and finance. ML models have been found to exhibit discrimination based on sensitive attributes such as gender, race, or disability. Assessing if an ML model is free of bias remains challenging to date, and by definition has to be done with sensitive user characteristics that are subject of anti-discrimination and data protection law. Existing libraries for fairness auditing of ML models offer no mechanism to protect the privacy of the audit data. We presen…
In this paper, we address the problem of privacy-preserving training and evaluation of neural networks in an $N$-party, federated learning setting. We propose a novel system, POSEIDON, the first of its kind in the regime of privacy-preserving neural network training. It employs multiparty lattice-based cryptography to preserve the confidentiality of the training data, the model, and the evaluation data, under a passive-adversary model and collusions between up to $N-1$ parties. To efficiently execute the secure backpropagation algorithm for training neural networks, we provide a generic packin…
In this paper, we present a secure multiparty computation (SMC) protocol for single-source shortest distances (SSSD) in undirected graphs, where the location of edges is public, but their length is private. The protocol works in the Arithmetic Black Box (ABB) model on top of the separator tree of the graph, achieving good time complexity if the subgraphs of the graph have small separators (which is the case for e.g. planar graphs); the achievable parallelism is significantly higher than that of classical SSSD algorithms implemented on top of an ABB. We implement our protocol on top of the Shar…
Differentially private noise mechanisms commonly use symmetric noise distributions. This is attractive both for achieving the differential privacy definition, and for unbiased expectations in the noised answers. However, there are contexts in which a noisy answer only has utility if it is conservative, that is, has known-signed error, which we call a padded answer. Seemingly, it is paradoxical to satisfy the DP definition with one-sided error, but we show how it is possible to bury the paradox into approximate DP's delta parameter. We develop a few mechanisms for one-sided padding mechanisms t…
University of Washington Tacoma（华盛顿大学塔科马分校）；Bar-Ilan University（巴伊兰大学）；Aarhus University（奥胡斯大学）；Huazhong University of Science and Technology（华中科技大学）
Machine learning (ML) is revolutionizing research and industry. Many ML applications rely on the use of large amounts of personal data for training and inference. Among the most intimate exploited data sources is electroencephalogram (EEG) data, a kind of data that is so rich with information that application developers can easily gain knowledge beyond the professed scope from unprotected EEG signals, including passwords, ATM PINs, and other intimate data. The challenge we address is how to engage in meaningful ML with EEG data while protecting the privacy of users. Hence, we propose cryptogra…
In this paper we introduce a novel gossiping primitive to support privacy preserving data analytics (PPDA). In contrast to existing computational PPDA primitives such as secure multiparty computation and data randomization based approaches, the proposed primitive `anonymous gossiping' is a communication primitive for privacy preserving personalized information aggregation complementing such traditional computational analytics. We realize this novel primitive by composing existing gossiping mechanisms for peer sampling & information aggregation and onion routing technique for establishing anony…
School of Engineering and Technology, University of Washington Tacoma（华盛顿大学塔科马分校工程与技术学院）；Faculty of Information Technology, Monash University（莫纳什大学信息技术学院）；Ghent University（根特大学）
Classification of personal text messages has many useful applications in surveillance, e-commerce, and mental health care, to name a few. Giving applications access to personal texts can easily lead to (un)intentional privacy violations. We propose the first privacy-preserving solution for text classification that is provably secure. Our method, which is based on Secure Multiparty Computation (SMC), encompasses both feature extraction from texts, and subsequent classification with logistic regression and tree ensembles. We prove that when using our secure text classification method, the applic…
University of Virginia（弗吉尼亚大学）；Facebook AI Research（Facebook AI研究院）
We introduce CryptGPU, a system for privacy-preserving machine learning that implements all operations on the GPU (graphics processing unit). Just as GPUs played a pivotal role in the success of modern deep learning, they are also essential for realizing scalable privacy-preserving deep learning. In this work, we start by introducing a new interface to losslessly embed cryptographic operations over secret-shared values (in a discrete domain) into floating-point operations that can be processed by highly-optimized CUDA kernels for linear algebra. We then identify a sequence of "GPU-friendly" cr…
This paper studies how a system operator and a set of agents securely execute a distributed projected gradient-based algorithm. In particular, each participant holds a set of problem coefficients and/or states whose values are private to the data owner. The concerned problem raises two questions: how to securely compute given functions; and which functions should be computed in the first place. For the first question, by using the techniques of homomorphic encryption, we propose novel algorithms which can achieve secure multiparty computation with perfect correctness. For the second question, …
