Especially in the Big Data era, the usage of different classification methods is increasing day by day. The success of these classification methods depends on the effectiveness of learning methods. Extreme learning machine (ELM) classification algorithm is a relatively new learning method built on feed-forward neural-network. ELM classification algorithm is a simple and fast method that can create a model from high-dimensional data sets. Traditional ELM learning algorithm implicitly assumes complete access to whole data set. This is a major privacy concern in most of cases. Sharing of private data (i.e. medical records) is prevented because of security concerns. In this research, we propose an efficient and secure privacy-preserving learning algorithm for ELM classification over data that is vertically partitioned among several parties. The new learning method preserves the privacy on numerical attributes, builds a classification model without sharing private data without disclosing the data of each party to others.
JD Finance America Corporation（京东金融美国公司）；Department of Electrical & Computer Engineering, University of Pittsburgh（匹兹堡大学电气与计算机工程系）；University of Pittsburgh（匹兹堡大学）
The privacy-preserving federated learning for vertically partitioned data has shown promising results as the solution of the emerging multi-party joint modeling application, in which the data holders (such as government branches, private finance and e-business companies) collaborate throughout the learning process rather than relying on a trusted third party to hold data. However, existing federated learning algorithms for vertically partitioned data are limited to synchronous computation. To improve the efficiency when the unbalanced computation/communication resources are common among the pa…
Preserving differential privacy has been well studied under centralized setting. However, it's very challenging to preserve differential privacy under multiparty setting, especially for the vertically partitioned case. In this work, we propose a new framework for differential privacy preserving multiparty learning in the vertically partitioned setting. Our core idea is based on the functional mechanism that achieves differential privacy of the released model by adding noise to the objective function. We show the server can simply dissect the objective function into single-party and cross-party…
IBM Research（IBM研究院）；University of Pittsburgh（匹兹堡大学）
Federated learning (FL) has been proposed to allow collaborative training of machine learning (ML) models among multiple parties where each party can keep its data private. In this paradigm, only model updates, such as model weights or gradients, are shared. Many existing approaches have focused on horizontal FL, where each party has the entire feature set and labels in the training data set. However, many real scenarios follow a vertically-partitioned FL setup, where a complete feature set is formed only when all the datasets from the parties are combined, and the labels are only available to…
As there is a growing interest in utilizing data across multiple resources to build better machine learning models, many vertically federated learning algorithms have been proposed to preserve the data privacy of the participating organizations. However, the efficiency of existing vertically federated learning algorithms remains to be a big problem, especially when applied to large-scale real-world datasets. In this paper, we present a fast, accurate, scalable and yet robust system for vertically federated random forest. With extensive optimization, we achieved $5\times$ and $83\times$ speed u…
University of Waterloo（滑铁卢大学）；Vector Institute（向量研究所）；Mayo Clinic（梅奥诊所）
Federated learning (FL) is a decentralized method enabling hospitals to collaboratively learn a model without sharing private patient data for training. In FL, participant hospitals periodically exchange training results rather than training samples with a central server. However, having access to model parameters or gradients can expose private training data samples. To address this challenge, we adopt secure multiparty computation (SMC) to establish a privacy-preserving federated learning framework. In our proposed method, the hospitals are divided into clusters. After local training, each h…
We present HDP-VFL, the first hybrid differentially private (DP) framework for vertical federated learning (VFL) to demonstrate that it is possible to jointly learn a generalized linear model (GLM) from vertically partitioned data with only a negligible cost, w.r.t. training time, accuracy, etc., comparing to idealized non-private VFL. Our work builds on the recent advances in VFL-based collaborative training among different organizations which rely on protocols like Homomorphic Encryption (HE) and Secure Multi-Party Computation (MPC) to secure computation and training. In particular, we analy…
Due to privacy concerns, multi-party gradient tree boosting algorithms have become widely popular amongst machine learning researchers and practitioners. However, limited existing works have focused on vertically partitioned datasets, and the few existing works are either not scalable or tend to leak information. Thus, in this work, we propose SSXGB which is a scalable and secure multi-party gradient tree boosting framework for vertically partitioned datasets with partially outsourced computations. Specifically, we employ an additive homomorphic encryption (HE) scheme for security. We design t…
Privacy is become major issue in distributed data mining. In the literature we can found many proposals of privacy preserving which can be divided into two major categories that is trusted third party and multiparty based privacy protocols. In case of trusted third party models the conventional asymmetric cryptographic based techniques will be used and in case of multi party based protocols data perturbed to make sure no other party to understand original data. In order to enhance security features by combining strengths of both models in this paper, we propose to use data perturbed techniques…
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both correct -- i.e., their outputs are bitwise equivalent to the cleartext execution -- and efficient -- they outperform the state-of-the-art protocols in both latency and scale. At the core of CrypTFlow2, we have new 2PC protocols for secure comparison and division, designed carefully to balance round and communication complexity for secure inference tasks. Using CrypTFlow2, we present the first secure inference over Image…
University of Oxford（牛津大学）；Queen Mary University of London（伦敦玛丽女王大学）；The Alan Turing Institute（艾伦·图灵研究所）；University of Warwick（华威大学）
Recently, there has been a wealth of effort devoted to the design of secure protocols for machine learning tasks. Much of this is aimed at enabling secure prediction from highly-accurate Deep Neural Networks (DNNs). However, as DNNs are trained on data, a key question is how such models can be also trained securely. The few prior works on secure DNN training have focused either on designing custom protocols for existing training algorithms, or on developing tailored training algorithms and then applying generic secure protocols. In this work, we investigate the advantages of designing training…
Secure multi-party computation (MPC) allows parties to perform computations on data while keeping that data private. This capability has great potential for machine-learning applications: it facilitates training of machine-learning models on private data sets owned by different parties, evaluation of one party's private model using another party's private data, etc. Although a range of studies implement machine-learning models via secure MPC, such implementations are not yet mainstream. Adoption of secure MPC is hampered by the absence of flexible software frameworks that "speak the language" …
Multi-party computation (MPC) is a branch of cryptography where multiple non-colluding parties execute a well designed protocol to securely compute a function. With the non-colluding party assumption, MPC has a cryptographic guarantee that the parties will not learn sensitive information from the computation process, making it an appealing framework for applications that involve privacy-sensitive user data. In this paper, we study training and inference of neural networks under the MPC setup. This is challenging because the elementary operations of neural networks such as the ReLU activation f…
Broad Institute of MIT and Harvard（麻省理工学院与哈佛大学博德研究所）
We detail distributed algorithms for scalable, secure multiparty linear regression and feature selection at essentially the same speed as plaintext regression. While the core geometric ideas are simple, the recognition of their broad utility when combined is novel. Our scheme opens the door to efficient and secure genome-wide association studies across multiple biobanks.
Secure sum computation of private data inputs is an interesting example of Secure Multiparty Computation (SMC) which has attracted many researchers to devise secure protocols with lower probability of data leakage. In this paper, we provide a novel protocol to compute the sum of individual data inputs with zero probability of data leakage when two neighbor parties collude to know the data of a middle party. We break the data block of each party into number of segments and redistribute the segments among parties before the computation. These entire steps create a scenario in which it becomes im…
Secure sum computation of private data inputs is an important component of Secure Multi party Computation (SMC).In this paper we provide a protocol to compute the sum of individual data inputs with zero probability of data leakage. In our proposed protocol we break input of each party into number of segments and change the arrangement of the parties such that in each round of the computation the neighbors are changed. In this protocol it becomes impossible for semi honest parties to know the private data of some other party.
Secure Multi-Party Computation (SMC) allows multiple parties to compute some function of their inputs without disclosing the actual inputs to one another. Secure sum computation is an easily understood example and the component of the various SMC solutions. Secure sum computation allows parties to compute the sum of their individual inputs without disclosing the inputs to one another. In this paper, we propose a modified version of our ck-Secure Sum protocol with more security when a group of the computing parties conspire to know the data of some party.
It is well known that, in theory, the general secure multi-party computation problem is solvable using circuit evaluation protocols. However, the communication complexity of the resulting protocols depend on the size of the circuit that expresses the functionality to be computed and hence can be impractical. Hence special solutions are needed for specific problems for efficiency reasons. The point inclusion problem in computational geometry is a special multiparty computation and has got many applications. Previous protocols for the secure point inclusion problem are not adequate. In this pape…
In this work, we study the problem of privacy preserving computation on PageRank algorithm. The idea is to enforce the secure multi party computation of the algorithm iteratively using homomorphic encryption based on Paillier scheme. In the proposed PageRank computation, a user encrypt its own graph data using asymmetric encryption method, sends the data set into different parties in a privacy-preserving manner. Each party computes its own encrypted entity, but learns nothing about the data at other parties.
We present attacks that show that unconditionally secure two-party classical computation is impossible for many classes of function. Our analysis applies to both quantum and relativistic protocols. We illustrate our results by showing the impossibility of oblivious transfer.
Multi-party learning is an indispensable technique for improving the learning performance via integrating data from multiple parties. Unfortunately, directly integrating multi-party data would not meet the privacy preserving requirements. Therefore, Privacy-Preserving Machine Learning (PPML) becomes a key research task in multi-party learning. In this paper, we present a new PPML method based on secure multi-party interactive protocol, namely Multi-party Secure Broad Learning System (MSBLS), and derive security analysis of the method. The existing PPML methods generally cannot simultaneously m…
In this work, we study how to securely evaluate the value of trading data without requiring a trusted third party. We focus on the important machine learning task of classification. This leads us to propose a provably secure four-round protocol that computes the value of the data to be traded without revealing the data to the potential acquirer. The theoretical results demonstrate a number of important properties of the proposed protocol. In particular, we prove the security of the proposed protocol in the honest-but-curious adversary model.
We derive algorithms for efficient secure numerical and logical operations using a recently introduced scheme for secure multi-party computation~\cite{sch15} in the semi-honest model ensuring statistical or perfect security. To derive our algorithms for trigonometric functions, we use basic mathematical laws in combination with properties of the additive encryption scheme in a novel way. For division and logarithm we use a new approach to compute a Taylor series at a fixed point for all numbers. All our logical operations such as comparisons and large fan-in AND gates are perfectly secure. Our…
The problem in which one of three pairwise interacting parties is required to securely compute a function of the inputs held by the other two, when one party may arbitrarily deviate from the computation protocol (active behavioral model), is studied. An information-theoretic characterization of unconditionally secure computation protocols under the active behavioral model is provided. A protocol for Hamming distance computation is provided and shown to be unconditionally secure under both active and passive behavioral models using the information-theoretic characterization. The difference betw…
To mitigate the scalability problem of decentralized cryptocurrencies such as Bitcoin and Ethereum, the payment channel, which allows two parties to perform secure coin transfers without involving the blockchain, has been proposed. The payment channel increases the transaction throughput of two parties to a level that is only limited by their network bandwidth. Recent proposals focus on extending the two-party payment channel to the N-party payment hub. Unfortunately, none of them can achieve efficiency, flexibility in the absence of a trusted third-party. In this paper, we propose Garou, a se…
The contribution of this short note, contains the following two parts: in the first part, we are able to show that the federate learning (FL) procedure presented by Kairouz et al. \cite{Kairouz1901}, is a random processing. Namely, an $m$-ary functionality for the FL procedure can be defined in the context of multi-party computation (MPC); Furthermore, an instance of FL protocol along Kairouz et al.'s definition can be viewed as an implementation of the defined $m$-ary functionality. As such, an instance of FL procedure is also an instance of MPC protocol. In short, FL is a subset of MPC. To p…
We introduce a new protocol for secure two-party computation of linear functions in the semi-honest model, based on coding techniques. We first establish a parallel between the second version of the wire-tap channel model and secure two-party computation. This leads us to our protocol, that combines linear coset coding and oblivious transfer techniques. Our construction requires the use of binary intersecting codes or $q$-ary minimal codes, which are also studied in this paper.
Central South University（中南大学）；Zhejiang University（浙江大学）；I4 data；Pennsylvania State University（宾夕法尼亚州立大学）；Facebook；Graz University of Technology（格拉茨技术大学）
Nowadays, as data becomes increasingly complex and distributed, data analyses often involve several related datasets that are stored on different servers and probably owned by different stakeholders. While there is an emerging need to provide these stakeholders with a full picture of their data under a global context, conventional visual analytical methods, such as dimensionality reduction, could expose data privacy when multi-party datasets are fused into a single site to build point-level relationships. In this paper, we reformulate the conventional t-SNE method from the single-site mode int…
Quantum conference is a process of securely exchanging messages between three or more parties, using quantum resources. A Measurement Device Independent Quantum Dialogue (MDI-QD) protocol, which is secure against information leakage, has been proposed (Quantum Information Processing 16.12 (2017): 305) in 2017, is proven to be insecure against intercept-and-resend attack strategy. We first modify this protocol and generalize this MDI-QD to a three-party quantum conference and then to a multi-party quantum conference. We also propose a protocol for quantum multi-party XOR computation. None of th…
During recent years with the increase of data and data analysis needs, privacy preserving data analysis methods have become of great importance. Researchers have proposed different methods for this purpose. Secure multi-party computation is one of such techniques that allows a group of parties to evaluate a function on their data without revealing the data. This is done by secret sharing approach, in which parties share a piece of their data using polynomials and after doing function evaluation on shares of data finally they do a Lagrange interpolation to get the result. Two approaches have be…
Privacy preserving multi-party computation has many applications in areas such as medicine and online advertisements. In this work, we propose a framework for distributed, secure machine learning among untrusted individuals. The framework consists of two parts: a two-step training protocol based on homomorphic addition and a zero knowledge proof for data validity. By combining these two techniques, our framework provides privacy of per-user data, prevents against a malicious user contributing corrupted data to the shared pool, enables each user to self-compute the results of the algorithm with…
The Universal Composability model (UC) by Canetti (FOCS 2001) allows for secure composition of arbitrary protocols. We present a quantum version of the UC model which enjoys the same compositionality guarantees. We prove that in this model statistically secure oblivious transfer protocols can be constructed from commitments. Furthermore, we show that every statistically classically UC secure protocol is also statistically quantum UC secure. Such implications are not known for other quantum security definitions. As a corollary, we get that quantum UC secure protocols for general multi-party com…
Secure Multi-Party Computation (SMPC) allows a set of parties to securely compute a functionality in a distributed fashion without the need for any trusted external party. Usually, it is assumed that the parties know each other and have already established authenticated channels among each other. However, in practice the parties sometimes must stay anonymous. In this paper, we conceptualize a framework that enables the repeated execution of an SMPC protocol for a given functionality such that the parties can keep their participation in the protocol executions private and at the same time be su…
The purpose of Secure Multi-Party Computation is to enable protocol participants to compute a public function of their private inputs while keeping their inputs secret, without resorting to any trusted third party. However, opening the public output of such computations inevitably reveals some information about the private inputs. We propose a measure generalising both Renyi entropy and g-entropy so as to quantify this information leakage. In order to control and restrain such information flows, we introduce the notion of function substitution which replaces the computation of a function that …
As far as we know, the literature on secure computation from cut-and-choose has focused on achieving computational security against malicious adversaries. It is unclear whether the idea of cut-and-choose can be adapted to secure computation with information-theoretic security. In this work we explore the possibility of using cut-and-choose in information theoretic setting for secure three-party computation (3PC). Previous work on 3PC has mainly focus on the semi-honest case, and is motivated by the observation that real-word deployments of multi-party computation (MPC) seem to involve few part…
A client wishes to outsource computation on confidential data to a network of parties. He does not trust a single party but believes that multiple parties do not collude. To solve this problem, we use the idea of treating one of the parties as a helper. A helper assists computation only. Often using more parties ensures confidentiality despite more corrupted parties. This does not hold for adding a helper. But a helper can in some cases lower the amount of communication asymptotically to the theoretical minimum of one bit per AND gate, improving significantly on schemes without a helper. It ca…
We propose a new approach to practical two-party computation secure against an active adversary. All prior practical protocols were based on Yao's garbled circuits. We use an OT-based approach and get efficiency via OT extension in the random oracle model. To get a practical protocol we introduce a number of novel techniques for relating the outputs and inputs of OTs in a larger construction. We also report on an implementation of this approach, that shows that our protocol is more efficient than any previous one: For big enough circuits, we can evaluate more than 20000 Boolean gates per secon…
E-voting systems (EVS)are having potential advantages over many existing voting schemes.Security, transparency, accuracy and reliability are the major concern in these systems.EVS continues to grow as the technology advances.It is inexpensive and efficient as the resources become reusable.Fast and accurate computation of results with voter privacy is the added advantage.In the proposed system we make use of secret sharing technique and secure multi party computation(SMC) to achieve security and reliability.Secret sharing is an important technique used for SMC. Multi-party computation is typica…
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…
Secure communication is a matter of genuine concern that includes means whereby entities can share information without a third party's interception. Key agreement protocols are one of the common approaches in which two or more parties can agree upon a key, which precludes undesired third parties from forcing a key choice on them. Over the past decade, chaos-based key agreement protocols have been studied and employed widely. Recently, Yoon and Jeon proposed a novel key agreement protocol based on chaotic maps and claimed security and practicality for their protocol. We find that Yoon-Jeon's pr…
In the secure two-party computation problem, two parties wish to compute a (possibly randomized) function of their inputs via an interactive protocol, while ensuring that neither party learns more than what can be inferred from only their own input and output. For semi-honest parties and information-theoretic security guarantees, it is well-known that, if only noiseless communication is available, only a limited set of functions can be securely computed; however, if interaction is also allowed over general communication primitives (multi-input/output channels), there are "complete" primitives …
Privacy of the outsourced data is one of the major challenge.Insecurity of the network environment and untrustworthiness of the service providers are obstacles of making the database as a service.Collection and storage of personally identifiable information is a major privacy concern.On-line public databases and resources pose a significant risk to user privacy, since a malicious database owner may monitor user queries and infer useful information about the customer.The challenge in data privacy is to share data with third-party and at the same time securing the valuable information from unaut…
Secure multi-party computation (SMPC) protocols allow several parties that distrust each other to collectively compute a function on their inputs. In this paper, we introduce a protocol that lifts classical SMPC to quantum SMPC in a composably and statistically secure way, even for a single honest party. Unlike previous quantum SMPC protocols, our proposal only requires very limited quantum resources from all but one party; it suffices that the weak parties, i.e. the clients, are able to prepare single-qubit states in the X-Y plane. The novel quantum SMPC protocol is constructed in a naturally…
Privacy-Preserving Detection of Rare Disease-Associated Cell Subsets via Secure Multi-Party Computation
Institute for Bioinformatics and Medical Informatics, University of Tübingen（蒂宾根大学生物信息学与医学信息学研究所）；Medical Data Privacy and Privacy-Preserving Machine Learning, University of Tübingen（蒂宾根大学医学数据隐私与隐私增强机器学习研究所）；University Hospital Aachen（亚琛大学医院）；Delft University of Technology（代尔夫特理工大学）
Since the negative result of Lo (Physical Review A, 1997), it has been left open whether there exist some functions that can be securely computed in two-party setting in quantum domain when one of the parties is malicious. In this paper, we for the first time, show that there are some functions for which secure two-party quantum computation is indeed possible for non-simultaneous channel model. This is in sharp contrast with the impossibility result of Ben -Or et al. (FOCS, 2006) in broadcast channel model. The functions we study are of two types - one is any function without an embedded XOR, …
Knowledge discovery is one of the main goals of Artificial Intelligence. This Knowledge is usually stored in databases spread in different environments, being a tedious (or impossible) task to access and extract data from them. To this difficulty we must add that these datasources may contain private data, therefore the information can never leave the source. Privacy Preserving Machine Learning (PPML) helps to overcome this difficulty, employing cryptographic techniques, allowing knowledge discovery while ensuring data privacy. K-means is one of the data mining techniques used in order to disc…
Rational secure multi-party computation (RSMC) means two or more rational parties to complete a function on private inputs. In the process, the rational parties choose strategies to maximize utility, which will cause players to maliciously execute the protocol and undermine the fairness and correctness of the protocol. To solve this problem, we leverage game theory to propose the direction entropy-based solution. First, we utilize the direction vector of the direction entropy to examine the player's strategy uncertainty and quantify its strategy from different dimensions. Specifically, when pa…
The cryptographic task of secure multi-party (classical) computation has received a lot of attention in the last decades. Even in the extreme case where a computation is performed between $k$ mutually distrustful players, and security is required even for the single honest player if all other players are colluding adversaries, secure protocols are known. For quantum computation, on the other hand, protocols allowing arbitrary dishonest majority have only been proven for $k=2$. In this work, we generalize the approach taken by Dupuis, Nielsen and Salvail (CRYPTO 2012) in the two-party setting t…
