Secure Multi-party Computation Techniques Research Articles

FedSQ: A Secure System for Federated Vector Similarity Queries

Vector databases have emerged as crucial tools for managing and retrieving representation embeddings of unstructured data. Given the explosive growth of data, vector data is often distributed and stored across multiple organizations. However, privacy concerns and regulations like GDPR present new challenges in collaborative and secure queries, also known as federated queries, over those vector data distributed across various data owners. Although existing research has attempted to enable such query services for low-dimensional data, such as relational and spatial data, these solutions can be inefficient in answering vector similarity queries involving high-dimensional data. Therefore, we are motivated to develop a new prototype system called FedSQ that (1) ensures privacy protection across data owners and (2) balances query efficiency and result accuracy when processing federated vector similarity queries. To achieve these goals, FedSQ utilizes advanced secure multi-party computation techniques to prevent information leakage during query processing and incorporates indexing and sampling based optimizations to strike a proper performance balance.

Compact: Approximating Complex Activation Functions for Secure Computation

Secure multi-party computation (MPC) techniques can be used to provide data privacy when users query deep neural network (DNN) models hosted on a public cloud. State-of-the-art MPC techniques can be directly leveraged for DNN models that use simple activation functions (AFs) such as ReLU. However, these techniques are ineffective and/or inefficient for the complex and highly non-linear AFs used in cutting-edge DNN models. We present Compact, which produces piece-wise polynomial approximations of complex AFs to enable their efficient use with state-of-the-art MPC techniques. Compact neither requires nor imposes any restriction on model training and results in near-identical model accuracy. To achieve this, we design Compact with input density awareness, and use an application specific simulated annealing type optimization to generate computationally more efficient approximations of complex AFs. We extensively evaluate Compact on four different machine-learning tasks with DNN architectures that use popular complex AFs silu, gelu, and mish. Our experimental results show that Compact incurs negligible accuracy loss while being 2x-5x computationally more efficient than state-of-the-art approaches for DNN models with large number of hidden layers. Our work accelerates easy adoption of MPC techniques to provide user data privacy even when the queried DNN models consist of a number of hidden layers, and trained over complex AFs.

Taypsi: Static Enforcement of Privacy Policies for Policy-Agnostic Oblivious Computation

Secure multiparty computation (MPC) techniques enable multiple parties to compute joint functions over their private data without sharing that data with other parties, typically by employing powerful cryptographic protocols to protect individual's data. One challenge when writing such functions is that most MPC languages force users to intermix programmatic and privacy concerns in a single application, making it difficult to change or audit a program's underlying privacy policy. Prior policy-agnostic MPC languages relied on dynamic enforcement to decouple privacy requirements from program logic. Unfortunately, the resulting overhead makes it difficult to scale MPC applications that manipulate structured data. This work proposes to eliminate this overhead by instead transforming programs into semantically equivalent versions that statically enforce user-provided privacy policies. We have implemented this approach in a new MPC language, called Taypsi; our experimental evaluation demonstrates that the resulting system features considerable performance improvements on a variety of MPC applications involving structured data and complex privacy policies.

Genomic Data Analysis with Variant of Secure Multi-Party Computation Technique

The increasing availability of genomic data for research purposes necessitates innovative approaches to ensure privacy while facilitating collaborative analysis. This study explores the integration of a variant of Secure Multi-Party Computation (SMPC) techniques into genomic data analysis. The conventional challenges of sharing sensitive genetic information among multiple entities, such as research institutions or healthcare providers, are addressed by leveraging advanced cryptographic protocols. The research focuses on the development and implementation of a secure framework for collaborative genomic data analysis using an adapted SMPC variant. This variant is designed to efficiently handle the complexities of genetic data while ensuring robust privacy preservation. By encrypting individual genomic inputs and enabling computations without revealing the raw data, the proposed SMPC variant facilitates joint analyses, contributing to advancements in personalized medicine, disease research, and genetic epidemiology. The variants of SMPC, namely oblivious transfer protocol, is used, this allows the receiver to obtain one out of several pieces of information forwarded by the sender without revealing which one they obtained. It can be integrated into SMPC protocols for enhancing the privacy with less effort and cost. The proposed mechanism involves the validation of the SMPC variant through simulations using real-world genomic datasets and assessing its performance in terms of computational efficiency and privacy preservation. Results from experiments demonstrate the feasibility and effectiveness of the proposed technique in enabling secure multi-party genomic data analysis. This research contributes to the evolving landscape of privacy-preserving techniques in genomics, offering a promising avenue for collaborative research without compromising the confidentiality of sensitive genetic information.

Confidential Training and Inference using Secure Multi-Party Computation on Vertically Partitioned Dataset

Digitalization across all spheres of life has given rise to issues like data ownership and privacy. Privacy-Preserving Machine Learning (PPML), an active area of research, aims to preserve privacy for machine learning (ML) stakeholders like data owners, ML model owners, and inference users. The Paper, CoTraIn-VPD, proposes private ML inference and training of models for vertically partitioned datasets with Secure Multi-Party Computation (SPMC) and Differential Privacy (DP) techniques. The proposed approach addresses complications linked with the privacy of various ML stakeholders dealing with vertically portioned datasets. This technique is implemented in Python using open-source libraries such as SyMPC (SMPC functions), PyDP (DP aggregations), and CrypTen (secure and private training). The paper uses information privacy measures, including mutual information and KL-Divergence, across different privacy budgets to empirically demonstrate privacy preservation with high ML accuracy and minimal performance cost.

Efficient and Secure Skyline Queries Over Vertical Data Federation

Skyline is a primitive operation in multi-objective decision applications and there is a growing demand to support such operations over a data federation, where the entire dataset is separately held by multiple data providers (a.k.a., silos). Data federations notably increase the amount of data available for data-intensive applications such as commercial recommendation and location based services. Yet they also challenge the conventional implementation of skyline queries because the raw data cannot be shared within the federation and the secure computation cross silos can be two or three orders of magnitude slower than plaintext computation. These constraints render existing solutions inefficient on data federation. In this work, we propose a novel local dominance based framework for efficient skyline queries over a vertical data federation. We decompose the skyline query into plaintext local dominance computations and secure result aggregations, which can perform as many computations in plaintext as possible without compromising security. We further propose a dedicate private set intersection based algorithm to accelerate the query processing. Extensive evaluations on both synthetic and real-world datasets show that compared with general-purpose secure multi-party computation techniques, our solutions reduce the time cost by up to 35.4× and communication cost by two orders of magnitude respectively.

Automatic Gate Opening System with Face Recognition

Despite the limitations of current technology, facial recognition from still or moving sources is developing into a useful tool for law enforcement, security, and counterterrorism applications. Currently, facial recognition shows promise and has been used in a small number of applications, The effectiveness of a facial recognition algorithm is examined in this assessment, specifically with regards to factors such as age, gender, ethnicity, facial characteristics, and lighting levels. Face recognition is being used more frequently as a non-intrusive identity verification technique. In this paper, we propose for the first time a strongly privacy-enhanced face recognition system that effectively uses secure multiparty computation techniques to conceal both the biometrics and the result from the server performing the matching operation. These issues can be easily solved by Explainable AI (XAI), and the solutions are clear to the end users. The proposed system is entirely implemented on a Raspberry Pi, enabling a full embedded application. With the aid of open-source libraries for training, defining, and running machine learning models like Tensorflow.js, Keras, and OpenCV, the application was created using Python and HTML on PyCharm/Visual Studio Code. An entire application can be run on a microcontroller, like the Raspberry Pi, which enables plug-and-play operation of the system at any time. The face detection subsystem, which is based on an improved PCA algorithm, can identify faces in moving vehicles and communicate with the vehicle's owner via GSM. The car's location is sent via GPS. This is the most reliable car security system because we can still locate the car even when it is lost and we can see the thief's face. The owner of the car is free to give the password to new drivers as well. This makes the car security system safer and more comfortable.

Secure and Accurate Summation of Many Floating-Point Numbers

Motivated by the importance of floating-point computations, we study the problem of securely and accurately summing many floating-point numbers. Prior work has focused on security absent accuracy or accuracy absent security, whereas our approach achieves both of them. Specifically, we show how to implement floating-point superaccumulators using secure multi-party computation techniques, so that a number of participants holding secret shares of floating-point numbers can accurately compute their sum while keeping the individual values private.

MPClan: Protocol Suite for Privacy-Conscious Computations

The growing volumes of data being collected and its analysis to provide better services are creating worries about digital privacy. To address privacy concerns and give practical solutions, the literature has relied on secure multiparty computation techniques. However, recent research over rings has mostly focused on the small-party honest-majority setting of up to four parties tolerating single corruption, noting efficiency concerns. In this work, we extend the strategies to support higher resiliency in an honest-majority setting with efficiency of the online phase at the centre stage. Our semi-honest protocol improves the online communication of the protocol of Damgård and Nielsen (CRYPTO’07) without inflating the overall communication. It also allows shutting down almost half of the parties in the online phase, thereby saving up to 50% in the system’s operational costs. Our maliciously secure protocol also enjoys similar benefits and requires only half of the parties, except for one-time verification towards the end, and provides security with fairness. To showcase the practicality of the designed protocols, we benchmark popular applications such as deep neural networks, graph neural networks, genome sequence matching, and biometric matching using prototype implementations. Our protocols, in addition to improved communication, aid in bringing up to 60–80% savings in monetary cost over prior work.

SPIKE: secure and private investigation of the kidney exchange problem

BackgroundThe kidney exchange problem (KEP) addresses the matching of patients in need for a replacement organ with compatible living donors. Ideally many medical institutions should participate in a matching program to increase the chance for successful matches. However, to fulfill legal requirements current systems use complicated policy-based data protection mechanisms that effectively exclude smaller medical facilities to participate. Employing secure multi-party computation (MPC) techniques provides a technical way to satisfy data protection requirements for highly sensitive personal health information while simultaneously reducing the regulatory burdens.ResultsWe have designed, implemented, and benchmarked SPIKE, a secure MPC-based privacy-preserving KEP protocol which computes a locally optimal solution by finding matching donor–recipient pairs in a graph structure. SPIKE matches 40 pairs in cycles of length 2 in less than 4 min and outperforms the previous state-of-the-art protocol by a factor of 400times in runtime while providing medically more robust solutions.ConclusionsWe show how to solve the KEP in a robust and privacy-preserving manner achieving significantly more practical performance than the current state-of-the-art (Breuer et al., WPES’20 and CODASPY’22). The usage of MPC techniques fulfills many data protection requirements on a technical level, allowing smaller health care providers to directly participate in a kidney exchange with reduced legal processes. As sensitive data are not leaving the institutions’ network boundaries, the patient data underlie a higher level of protection than in the currently employed (centralized) systems. Furthermore, due to reduced legal barriers, the proposed decentralized system might be simpler to implement in a transnational, intereuropean setting with mixed (national) data protecion laws.

Privacy-Preserving Collaborative Computation for Human Activity Recognition

Human Activity Recognition (HAR) enables computer systems to assist users with their tasks and improve their quality of life in rehabilitation, daily life tracking, fitness, and cognitive disorder therapy. It is a hot topic in the field of machine learning, and HAR is gaining more attention among researchers due to its unique societal and economic advantages. This paper focuses on a collaborative computation scenario where a group of participants will securely and collaboratively train an accurate HAR model. The training process requires collecting a massive number of personal activity features and labels, which raises privacy problems. We decentralize the training process locally to each client in order to ensure the privacy of training data. Furthermore, we use an advanced secure aggregation algorithm to ensure that malicious participants cannot extract private information from the updated parameters even during the aggregation phase. Edge computing nodes have been introduced into our system to address the problem of data generation devices’ insufficient computing power. We replace the traditional central server with smart contract to make the system more robust and secure. We achieve the verifiability of the packaged nodes using the publicly auditability feature of blockchain. According to the experimental data, the accuracy of the HAR model trained by our proposed framework reaches 93.24%, which meets the applicability requirements. The use of secure multiparty computation techniques unavoidably increases training time, and experimental results show that a round of iterations takes 36.4 seconds to execute, which is still acceptable.

Hu-Fu

Data isolation has become an obstacle to scale up query processing over big data, since sharing raw data among data owners is often prohibitive due to security concerns. A promising solution is to perform secure queries over a federation of multiple data owners leveraging secure multi-party computation (SMC) techniques, as evidenced by recent federation work over relational data. However, existing solutions are highly inefficient on spatial queries due to excessive secure distance operations for query processing and their usage of general-purpose SMC libraries for secure operation implementation. In this paper, we propose Hu-Fu, the first system for efficient and secure spatial query processing on a data federation. The idea is to decompose the secure processing of a spatial query into as many plaintext operations and as few secure operations as possible, where fewer secure operators are involved and all secure operators are implemented dedicatedly. As a working system, Hu-Fu supports not only query input in native SQL, but also heterogeneous spatial databases ( e.g. , PostGIS, Simba, GeoMesa, and SpatialHadoop) at the backend. Extensive experiments show that Hu-Fu usually outperforms the state-of-the-arts in running time and communication cost while guaranteeing security.

Post-quantum secure multi-party private set-intersection in star network topology

In many realistic scenarios, participants wish to perform some secret set operations such as intersection, union, cardinality of intersection, etc. on their private data sets. Private Set Intersection (PSI) plays a major role in addressing such problems. PSI is one of the widely used secure multi-party computation technique that allows the participants to securely compute the intersection of their private input sets and nothing beyond that. It is generally executed between two parties. When the number of entities is more than two, it is known as multi-party PSI (MPSI). Today, the security of all the existing MPSI protocols are based on number theoretic assumptions. However, these will become insecure once large enough quantum computers are built. As a consequence, designing of quantum computer resistant MPSI becomes an interesting direction of research work. This paper addresses the issue by presenting the first post-quantum MPSI protocol in the so-called star network topology, using lattice-based public key encryption scheme. We utilize space-efficient probabilistic data structure (Bloom filter) as building blocks of our design. It attains security in standard model (without random oracles) under the decisional learning with errors (DLWE) assumption.

Preserving Privacy of Software-Defined Networking Policies by Secure Multi-Party Computation

In software-defined networking (SDN), controllers are sinks of information such as network topology collected from switches. Organizations often like to protect their internal network topology and keep their network policies private. We borrow techniques from secure multi-party computation (SMC) to preserve the privacy of policies of SDN controllers about status of routers. On the other hand, the number of controllers is one of the most important concerns in scalability of SMC application in SDNs. To address this issue, we formulate an optimization problem to minimize the number of SDN controllers while considering their reliability in SMC operations. We use Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to determine the optimal number of controllers, and simulate SMC for typical SDNs with this number of controllers. Simulation results show that applying the SMC technique to preserve the privacy of organization policies causes only a little delay in SDNs, which is completely justifiable by the privacy obtained.

PrivEdge: From Local to Distributed Private Training and Prediction

Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user data, which could lead to significant privacy concerns when dealing with sensitive personal data. To address this problem, we propose PrivEdge, a technique for privacy-preserving MLaaS that safeguards the privacy of users who provide their data for training, as well as users who use the prediction service. With PrivEdge, each user independently uses their private data to locally train a one-class reconstructive adversarial network that succinctly represents their training data. As sending the model parameters to the service provider in the clear would reveal private information, PrivEdge secret-shares the parameters among two non-colluding MLaaS providers, to then provide cryptographically private prediction services through secure multi-party computation techniques. We quantify the benefits of PrivEdge and compare its performance with state-of-the-art centralised architectures on three privacy-sensitive image-based tasks: individual identification, writer identification, and handwritten letter recognition. Experimental results show that PrivEdge has high precision and recall in preserving privacy, as well as in distinguishing between private and non-private images. Moreover, we show the robustness of PrivEdge to image compression and biased training data. The source code is available at https://github.com/smartcameras/PrivEdge .

Privacy Techniques for Edge Computing Systems

In an edge-enabled data management and computing environment, it is critical to ensure the privacy of the information acquired, processed, and exchanged among the different parties. The problem is complex because of the large scale, mobility, device, and protocol heterogeneity. Also, unlike in conventional environments, communication may be fragmented and portions of the environment can be physically unprotected. To date, there are several privacy-enhancing techniques, such as secure multiparty computation techniques, private information retrieval (PIR), and data sanitization techniques. However, there is not a single technique that works for all possible uses of the data in edge systems. In addition, these techniques are computationally expensive and thus may not be suitable for edge devices. In this paper, we first cover basic privacy building blocks, including differential privacy and homomorphic encryption. We then discuss privacy solutions specific to three different types of data use that are relevant for edge-based applications: data aggregation techniques, point-of-interest (POI) services and traffic information services, and crowdsourcing. These applications have been selected as they provide a broad spectrum of edge computing applications. Throughout this paper, we outline open research directions.

Hybrid Private Record Linkage

Private record linkage protocols allow multiple parties to exchange matching records, which refer to the same entities or have similar values, while keeping the non-matching ones secret. Conventional protocols are based on computationally expensive cryptographic primitives and therefore do not scale. To address these scalability issues, hybrid protocols have been proposed that combine differential privacy techniques with secure multiparty computation techniques. However, a drawback of such protocols is that they disclose to the parties both the matching records and the differentially private synopses of the datasets involved in the linkage. Consequently, differential privacy is no longer always satisfied. To address this issue, we propose a novel framework that separates the private synopses from the matching records. The two parties do not access the synopses directly, but still use them to efficiently link records. We theoretically prove the security of our framework under the state-of-the-art privacy notion of differential privacy for record linkage (DPRL). In addition, we develop a simple but effective strategy for releasing private synopses. Extensive experimental results show that our framework is superior to the existing methods in terms of efficiency.

Secure Multiparty Computation and Trusted Hardware: Examining Adoption Challenges and Opportunities

When two or more parties need to compute a common result while safeguarding their sensitive inputs, they use secure multiparty computation (SMC) techniques such as garbled circuits. The traditional enabler of SMC is cryptography, but the significant number of cryptographic operations required results in these techniques being impractical for most real-time, online computations. Trusted execution environments (TEEs) provide hardware-enforced isolation of code and data in use, making them promising candidates for making SMC more tractable. This paper revisits the history of improvements to SMC over the years and considers the possibility of coupling trusted hardware with SMC. This paper also addresses three open challenges: (1) defeating malicious adversaries, (2) mobile-friendly TEE-supported SMC, and (3) a more general coupling of trusted hardware and privacy-preserving computation.

Towards practical privacy-preserving genome-wide association study

BackgroundThe deployment of Genome-wide association studies (GWASs) requires genomic information of a large population to produce reliable results. This raises significant privacy concerns, making people hesitate to contribute their genetic information to such studies.ResultsWe propose two provably secure solutions to address this challenge: (1) a somewhat homomorphic encryption (HE) approach, and (2) a secure multiparty computation (MPC) approach. Unlike previous work, our approach does not rely on adding noise to the input data, nor does it reveal any information about the patients. Our protocols aim to prevent data breaches by calculating the χ2 statistic in a privacy-preserving manner, without revealing any information other than whether the statistic is significant or not. Specifically, our protocols compute the χ2 statistic, but only return a yes/no answer, indicating significance. By not revealing the statistic value itself but only the significance, our approach thwarts attacks exploiting statistic values. We significantly increased the efficiency of our HE protocols by introducing a new masking technique to perform the secure comparison that is necessary for determining significance.ConclusionsWe show that full-scale privacy-preserving GWAS is practical, as long as the statistics can be computed by low degree polynomials. Our implementations demonstrated that both approaches are efficient. The secure multiparty computation technique completes its execution in approximately 2 ms for data contributed by one million subjects.

Protecting Patient Privacy in Genomic Analysis

Patient genomes are interpretable only in the context of other genomes. However, privacy concerns over genetic data oftentimes deter individuals from contributing their genomes to scientific studies and prevent researchers from sharing their data with the scientific community. In this talk, I will describe how we can leverage secure multiparty computation techniques from modern cryptography to perform useful scientific computations on genomic data while protecting the privacy of the participants' genomes. In multiple real scenarios, our methods successfully identified the disease-causing genes and even discovered previously unrecognized disease genes, all while keeping nearly all of the participants' most sensitive genomic information private. We believe that our techniques will help make currently restricted data more readily available to the scientific community and enable individuals to contribute their genomes to a study without compromising their personal privacy.
 The material from this talk is based on joint works with Gill Bejerano, Bonnie Berger, Johannes A. Birgmeier, Dan Boneh, Hyunghoon Cho, and Karthik A. Jagadeesh.