The performance of deep learning models highly depends on the amount of training data. It is common practice for today's data holders to merge their datasets and train models collaboratively, which yet poses a threat to data privacy. Different from existing methods such as secure multi-party computation (MPC) and federated learning (FL), we find representation learning has unique advantages in collaborative learning due to the lower communication overhead and task-independency. However, data representations face the threat of model inversion attacks. In this article, we formally define the collaborative learning scenario, and quantify data utility and privacy. Then we present ARS, a collaborative learning framework wherein users share representations of data to train models, and add imperceptible adversarial noise to data representations against reconstruction or attribute extraction attacks. By evaluating ARS in different contexts, we demonstrate that our mechanism is effective against model inversion attacks, and achieves a balance between privacy and utility. The ARS framework has wide applicability. First, ARS is valid for various data types, not limited to images. Second, data representations shared by users can be utilized in different tasks. Third, the framework can be easily extended to the vertical data partitioning scenario.
Los Andes University（洛斯安第斯大学）；Rappi（Rappi公司）；Amazon（亚马逊）
Privacy-preserving machine learning in data-sharing processes is an ever-critical task that enables collaborative training of Machine Learning (ML) models without the need to share the original data sources. It is especially relevant when an organization must assure that sensitive data remains private throughout the whole ML pipeline, i.e., training and inference phases. This paper presents an innovative framework that uses Representation Learning via autoencoders to generate privacy-preserving embedded data. Thus, organizations can share the data representation to increase machine learning mo…
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；JZTData Technology（JZTData科技公司 (JZTData Technology)）
With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical applications. On the one hand, although most cryptographic methods are provable secure, they bring heavy computation and communication. On the other hand, the security of many relatively efficient private methods (e.g., federated learning and split learning) is being questioned, since they are non-provable secure. Inspired by previous work on privacy-preserving machine learning, …
Ant Group（蚂蚁集团）；Shandong Normal University（山东师范大学）；Alibaba Group（阿里巴巴集团）
Logistic Regression (LR) is the most widely used machine learning model in industry for its efficiency, robustness, and interpretability. Due to the problem of data isolation and the requirement of high model performance, many applications in industry call for building a secure and efficient LR model for multiple parties. Most existing work uses either Homomorphic Encryption (HE) or Secret Sharing (SS) to build secure LR. HE based methods can deal with high-dimensional sparse features, but they incur potential security risks. SS based methods have provable security, but they have efficiency is…
This paper investigates how secure information sharing with external vendors can be achieved in an Industrial Internet of Things (IIoT). It also identifies necessary security requirements for secure information sharing based on identified security challenges stated by the industry. The paper then proposes a roadmap for improving security in IIoT which investigates both short-term and long-term solutions for protecting IIoT devices. The short-term solution is mainly based on integrating existing good practices. The paper also outlines a long term solution for protecting IIoT devices with fine-g…
Secure Multiparty Computation (MPC) can improve the security and privacy of data owners while allowing analysts to perform high quality analytics. Secure aggregation is a secure distributed mechanism to support federated deep learning without the need for trusted third parties. In this paper we present a highly performant secure aggregation protocol with sub-linear communication complexity. Our protocol achieves greater communication and computation efficiencies through a group-based approach. It is similar to secret sharing protocols extended to vectors of values-aka gradients-but within grou…
Robust and Actively Secure Serverless Collaborative Learning
Northwestern University（西北大学）；CISPA（CISPA亥姆霍兹信息安全中心）；Google（谷歌）；University of Toronto and Vector Institute（多伦多大学与向量研究所）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Secure E-voting is a challenging protocol. Several approaches based on homomorphic crypto systems, mix-nets blind signatures are proposed in the literature .But most of them need complicated homomorphic encryption which involves complicated encryption decryption process and key management which is not efficient. In this paper we propose a secure and efficient E-voting scheme based on secret sharing homomorphism. Here E-voting is viewed as special case of multi party computation where several voters jointly compute the result without revealing his vote. Secret sharing schemes are good alternati…
In recent years, gradient boosted decision tree learning has proven to be an effective method of training robust models. Moreover, collaborative learning among multiple parties has the potential to greatly benefit all parties involved, but organizations have also encountered obstacles in sharing sensitive data due to business, regulatory, and liability concerns. We propose Secure XGBoost, a privacy-preserving system that enables multiparty training and inference of XGBoost models. Secure XGBoost protects the privacy of each party's data as well as the integrity of the computation with the help…
In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data. We consider a variant of this problem, where the input data can be shared for machine learning training purposes, but the data are also encrypted so that they cannot be recovered by other parties. We present a rotation based method using flow model, and theoretically justified its security. We demonstrate the effectiveness of our method in different scenarios, including supervised secure model training, and unsupervised generative model training. Our code is ava…
Johannes Gutenberg University Mainz（约翰内斯·古腾堡-美因茨大学）
Deep learning (DL) approaches are achieving extraordinary results in a wide range of domains, but often require a massive collection of private data. Hence, methods for training neural networks on the joint data of different data owners, that keep each party's input confidential, are called for. We address a specific setting in federated learning, namely that of deep learning from horizontally distributed data with a limited number of parties, where their vulnerable intermediate results have to be processed in a privacy-preserving manner. This setting can be found in medical and healthcare as …
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…
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…
Hardware enclaves rely on a disjoint memory model, which maps each physical address to an enclave to achieve strong memory isolation. However, this severely limits the performance and programmability of enclave programs. While some prior work proposes enclave memory sharing, it does not provide a formal model or verification of their designs. This paper presents Cerberus, a formal approach to secure and efficient enclave memory sharing. To reduce the burden of formal verification, we compare different sharing models and choose a simple yet powerful sharing model. Based on the sharing model, Ce…
Data security and availability for operational use are frequently seen as conflicting goals. Research on searchable encryption and homomorphic encryption are a start, but they typically build from encryption methods that, at best, provide protections based on problems assumed to be computationally hard. By contrast, data encoding methods such as secret sharing provide information-theoretic data protections. Archives that distribute data using secret sharing can provide data protections that are resilient to malicious insiders, compromised systems, and untrusted components. In this paper, we cr…
In this letter we propose Meta-key, a data-sharing mechanism that enables users share their encrypted data under a blockchain-based decentralized storage architecture. All the data-encryption keys are encrypted by the owner's public key and put onto the blockchain for safe and secure storage and easy key-management. Encrypted data are stored in dedicated storage nodes and proxy re-encryption mechanism is used to ensure secure data-sharing in the untrusted environment. Security analysis of our model shows that the proxy re-encryption adopted in our system is naturally free from collusion-attack…
Although sharing data across organizations is often advocated as a promising way to enhance cybersecurity, collaborative initiatives are rarely put into practice owing to confidentiality, trust, and liability challenges. In this paper, we investigate whether collaborative threat mitigation can be realized via a controlled data sharing approach, whereby organizations make informed decisions as to whether or not, and how much, to share. Using appropriate cryptographic tools, entities can estimate the benefits of collaboration and agree on what to share in a privacy-preserving way, without having…
We consider the problem of sharing sensitive or valuable files across users while partially relying on a common, untrusted third-party, e.g., a Cloud Storage Provider (CSP). Although users can rely on a secure peer-to-peer (P2P) channel for file sharing, this introduces potential delay on the data transfer and requires the sender to remain active and connected while the transfer process occurs. Instead of using the P2P channel for the entire file, users can upload information about the file on a common CSP and share only the essential information that enables the receiver to download and recov…
Ant Financial Services Group（蚂蚁金融服务集团）；Shandong Normal University（山东师范大学）
Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns. On one hand, potential gains are highly anticipated if different organizations could somehow collaboratively share their data for technological improvements. On the other hand, data security concerns may arise for both data holders and data providers due to commercial or sociological concerns. To make a balance between technical improvements and security limitations, we implement secure and scalable protocols for multiple data holders …
The 5G network would fuel next-gen, bandwidth-heavy technologies such as automation, IoT, and AI on the factory floor. It will improve efficiency by powering AR overlays in workflows, as well as ensure safer practices and reduce the number of defects through predictive analytics and real-time detection of damage. The Dynamic Spectrum Sharing (DSS) in 5G networks will permit 5G NR and 4G LTE to coexist and will provide cost-effective and efficient solutions that enable a smooth transition from 4G to 5G. However, this increases the attack surface in the 5G networks. To the best of our knowledge,…
The rising need of secret image sharing with high security has led to much advancement in lucrative exchange of important images which contain vital and confidential information. Multi secret image sharing system (MSIS) is an efficient and robust method for transmitting one or more secret images securely. In recent research, n secret images are encrypted into n or n+ 1 shared images and stored in different database servers. The decoder has to receive all n or n+1 encrypted images to reproduce the secret image. One can recover partial secret information from n-1 or fewer shared images, which po…
Verifiable Secret-Sharing (VSS) is a fundamental primitive in secure distributed computing. It is used as a building block in several distributed computing tasks, such as Byzantine agreement and secure multi-party computation. In this article, we consider VSS schemes with perfect security, tolerating computationally unbounded adversaries. We comprehensively survey the existing perfectly-secure VSS schemes in three different communication settings, namely synchronous, asynchronous and hybrid setting and provide full details of the existing schemes in these settings. The aim of this survey is to…
With the advent of cloud technologies, there is a growing number of easy-to-use services to store files and share them with other cloud users. By providing security features, cloud service providers try to encourage users to store personal files or corporate documents on their servers. However, their server-side encryption solutions are not satisfactory when the server itself is not trusted. Although, there are several client-side solutions to provide security for cloud sharing, they are not used extensively because of usability issues in key management. In this paper, we propose TwinCloud whi…
This paper reports on the development and evaluation of a prototype blockchain solution for private and secure individual omics health data management and sharing. This solution is one output of a multidisciplinary project investigating the social, data and technical issues surrounding application of blockchain technology in the context of personalized healthcare research. The project studies potential ethical, legal, social and cognitive constraints of self-sovereign healthcare data management and sharing, and whether such constraints can be addressed through careful user interface design of …
Collaborative learning allows participants to jointly train a model without data sharing. To update the model parameters, the central server broadcasts model parameters to the clients, and the clients send updating directions such as gradients to the server. While data do not leave a client device, the communicated gradients and parameters will leak a client's privacy. Attacks that infer clients' privacy from gradients and parameters have been developed by prior work. Simple defenses such as dropout and differential privacy either fail to defend the attacks or seriously hurt test accuracy. We …
Getting access to labelled datasets in certain sensitive application domains can be challenging. Hence, one often resorts to transfer learning to transfer knowledge learned from a source domain with sufficient labelled data to a target domain with limited labelled data. However, most existing transfer learning techniques only focus on one-way transfer which brings no benefit to the source domain. In addition, there is the risk of a covert adversary corrupting a number of domains, which can consequently result in inaccurate prediction or privacy leakage. In this paper we construct a secure and …
The first construction of strongly secure quantum ramp secret sharing by Zhang and Matsumoto had an undesirable feature that the dimension of quantum shares must be larger than the number of shares. By using algebraic curves over finite fields, we propose a new construction in which the number of shares can become arbitrarily large for fixed dimension of shares.
As data collection and analysis become critical functions for many cloud applications, proper data sharing with approved parties is required. However, the traditional data sharing scheme through centralized data escrow servers may sacrifice owners' privacy and is weak in security. Mainly, the servers physically own all data while the original data owners have only virtual ownership and lose actual access control. Therefore, we propose a 3-layer SSE-ABE-AES (3LSAA) cryptography-based privacy-protected data-sharing protocol based on the assumption that servers are honest-but-curious. The 3LSAA p…
Recently, coordinated attack campaigns started to become more widespread on the Internet. In May 2017, WannaCry infected more than 300,000 machines in 150 countries in a few days and had a large impact on critical infrastructure. Existing threat sharing platforms cannot easily adapt to emerging attack patterns. At the same time, enterprises started to adopt machine learning-based threat detection tools in their local networks. In this paper, we pose the question: \emph{What information can defenders share across multiple networks to help machine learning-based threat detection adapt to new coo…
Electronic medical records (EMRs) are critical, highly sensitive private information in healthcare, and need to be frequently shared among peers. Blockchain provides a shared, immutable and transparent history of all the transactions to build applications with trust, accountability and transparency. This provides a unique opportunity to develop a secure and trustable EMR data management and sharing system using blockchain. In this paper, we present our perspectives on blockchain based healthcare data management, in particular, for EMR data sharing between healthcare providers and for research …
We present a supervised secure entanglement sharing protocol via tripartite W states for faithful quantum teleportation. By guaranteeing a secure entanglement distribution in the charge of a third believed supervisor, quantum information of an unknown state of a 2-level particle can be faithfully teleported from the sender to the remote receiver via the Bell states distilled from the tripartite W states. We emphasize that reliable teleportation after our protocol between two communication parties depends on the agreement of the supervisor to cooperate via taking the W states as both the quantu…
The intelligent vehicle (IV) has become a promising technology that could revolutionize our life in smart cities sooner or later. However, it yet suffers from many security vulnerabilities. Traditional security methods are incapable to secure the IV data sharing against malicious attacks. Blockchain, as expected by both research and industry communities, has emerged as a good solution to address these issues. The major issues in IV data sharing are trust, data accuracy and reliability of data sharing in the communication channel. Blockchain technology, previously working for the cryptocurrency…
Timely sharing of electronic health records (EHR) across providers is essential and significance in facilitating medical researches and prompt patients' care. With sharing, it is crucial that patients can control who can access their data and when, and guarantee the security and privacy of their data. In current literature, various system models, cryptographic techniques and access control mechanisms are proposed which requires patient's consent before sharing. However, they mostly focus on patient is available to authorize the access of the EHR upon requested. This is impractical given that t…
Cloud computing has been a dominant paradigm for a variety of information processing platforms, particularly for enabling various popular applications of sharing economy. However, there is a major concern regarding data privacy on these cloud-based platforms. This work presents novel cloud-based privacy-preserving solutions to support collaborative consumption applications for sharing economy. In typical collaborative consumption, information processing platforms need to enable fair cost-sharing among multiple users for utilizing certain shared facilities and communal services. Our cloud-based…
Many organizations stand to benefit from pooling their data together in order to draw mutually beneficial insights -- e.g., for fraud detection across banks, better medical studies across hospitals, etc. However, such organizations are often prevented from sharing their data with each other by privacy concerns, regulatory hurdles, or business competition. We present Senate, a system that allows multiple parties to collaboratively run analytical SQL queries without revealing their individual data to each other. Unlike prior works on secure multi-party computation (MPC) that assume that all part…
Dynaswap project reports on developing a coherently integrated and trustworthy holistic secure workflow protection architecture for cyberinfrastructures which can be used on virtual machines deployed through cyberinfrastructure (CI) services such as JetStream. This service creates a user-friendly cloud environment designed to give researchers access to interactive computing and data analysis resources on demand. The Dynaswap cybersecurity architecture supports roles, role hierarchies, and data hierarchies, as well as dynamic changes of roles and hierarchical relations within the scientific inf…
We present a relational MPC framework for secure collaborative analytics on private data with no information leakage. Our work targets challenging use cases where data owners may not have private resources to participate in the computation, thus, they need to securely outsource the data analysis to untrusted third parties. We define a set of oblivious operators, explain the secure primitives they rely on, and analyze their costs in terms of operations and inter-party communication. We show how these operators can be composed to form end-to-end oblivious queries, and we introduce logical and ph…
The emergence of cloud computing provides a new computing paradigm for users -- massive and complex computing tasks can be outsourced to cloud servers. However, the privacy issues also follow. Fully homomorphic encryption shows great potential in privacy-preserving computation, yet it is not ready for practice. At present, secure multiparty computation (MPC) remains mainly approach to deal with sensitive data. In this paper, following the secret sharing based MPC paradigm, we propose a secure 2-party computation scheme, in which cloud servers can securely evaluate functions with high efficienc…
There is a great interest in many approaches towards blockchain in providing a solution to record transactions in a decentralized way. However, there are some limitations when storing large files or documents on the blockchain. In order to meet the requirements of storing relatively large data, a decentralized storage medium is produced. IPFS is a distributed file system which is content-addressable. It works very similar to the blockchain network. There are some attempts which take advantage of the blockchain concept and IPFS to design new approaches. Unfortunately, there are some inefficienc…
Spatial data sharing plays a significant role in opening data research and promoting government agency transparency. However, valuable spatial data, like high-precision geographic information and personal traffic records, cannot be made public because they may incur leakage risks such as intrusion, theft, and the unauthorised sale of proprietary information. When participants with confidential data distrust each other but want to use the other datasets for calculations, the most common solution is to provide their original data to a trusted third party. However, the trusted third party frequen…
Artificial Intelligence (AI) incorporating genetic and medical information have been applied in disease risk prediction, unveiling disease mechanism, and advancing therapeutics. However, AI training relies on highly sensitive and private data which significantly limit their applications and robustness evaluation. Moreover, the data access management after sharing across organization heavily relies on legal restriction, and there is no guarantee in preventing data leaking after sharing. Here, we present Genie, a secure AI platform which allows AI models to be trained on medical data securely. T…
Ant Financial Services Group（蚂蚁金服集团）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Peking University（北京大学）；Alibaba security（阿里巴巴安全（集团））
Nowadays, privacy preserving machine learning has been drawing much attention in both industry and academy. Meanwhile, recommender systems have been extensively adopted by many commercial platforms (e.g. Amazon) and they are mainly built based on user-item interactions. Besides, social platforms (e.g. Facebook) have rich resources of user social information. It is well known that social information, which is rich on social platforms such as Facebook, are useful to recommender systems. It is anticipated to combine the social information with the user-item ratings to improve the overall recommen…
As ATM applications deploy for a banking system, the need to secure communications will become critical. However, multicast protocols do not fit the point-to-point model of most network security protocols which were designed with unicast communications in mind. In recent years, we have seen the emergence and the growing of ATMs (Automatic Teller Machines) in banking systems. Many banks are extending their activity and increasing transactions by using ATMs. ATM will allow them to reach more customers in a cost effective way and to make their transactions fast and efficient. However, communicati…
Providing functionalities that allow online social network users to manage in a secure and private way the publication of their information and/or resources is a relevant and far from trivial topic that has been under scrutiny from various research communities. In this work, we provide a framework that allows users to define highly expressive access policies to their resources in a way that the enforcement does not require the intervention of a (trusted or not) third party. This is made possible by the deployment of a newly defined cryptographic primitives that provides - among other things - …
