Secure multiparty computation

Lindell, Yehuda

doi:10.1145/3387108

Cited by 102 publications

(41 citation statements)

References 37 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notice that we chose to present cryptographic concepts with a focus on intuition, so as not to burden the reader with an unnecessary level of formalism. The reader can refer to [36,37] for a more formal discussion of general cryptographic concepts (including cryptographic hash functions, homomorphic encryption, and secret sharing), and to [38,39] for an in-depth discussion of MPC and Secret Sharing.…”

Section: Aim and Assumptionsmentioning

confidence: 99%

Privacy-preserving dataset combination and Lasso regression for healthcare predictions

Egmond

Spini

Galiën

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Recent developments in machine learning have shown its potential impact for clinical use such as risk prediction, prognosis, and treatment selection. However, relevant data are often scattered across different stakeholders and their use is regulated, e.g. by GDPR or HIPAA. As a concrete use-case, hospital Erasmus MC and health insurance company Achmea have data on individuals in the city of Rotterdam, which would in theory enable them to train a regression model in order to identify high-impact lifestyle factors for heart failure. However, privacy and confidentiality concerns make it unfeasible to exchange these data. Methods This article describes a solution where vertically-partitioned synthetic data of Achmea and of Erasmus MC are combined using Secure Multi-Party Computation. First, a secure inner join protocol takes place to securely determine the identifiers of the patients that are represented in both datasets. Then, a secure Lasso Regression model is trained on the securely combined data. The involved parties thus obtain the prediction model but no further information on the input data of the other parties. Results We implement our secure solution and describe its performance and scalability: we can train a prediction model on two datasets with 5000 records each and a total of 30 features in less than one hour, with a minimal difference from the results of standard (non-secure) methods. Conclusions This article shows that it is possible to combine datasets and train a Lasso regression model on this combination in a secure way. Such a solution thus further expands the potential of privacy-preserving data analysis in the medical domain.

show abstract

Section: Aim and Assumptionsmentioning

confidence: 99%

Privacy-preserving dataset combination and Lasso regression for healthcare predictions

Egmond

Spini

Galiën

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Security guarantees of the protocols used in distributed systems, where multiple parties interact, often rely on the ideal-real world simulation paradigm [20][21][22]. This paradigm considers an ideal scenario where an ideal functionality (i.e., inviolable third-party) receives data from participants, computes a function in a centralized way, and sends back the result of the execution.…”

Section: Adversarial Modelmentioning

confidence: 99%

“…Each of these has particular requirements and benefits, and thus they are usually combined. We refer to the recent work by Lindell [20] for a detailed description of SMPC. Oblivious Transfer (OT) is a 2-party cryptographic protocol allowing a receiver to request k out of n pieces from a sender.…”

Section: Secure Multiparty Computationmentioning

confidence: 99%

SoK: Privacy-Preserving Computation Techniques for Deep Learning

Cabrero-Holgueras

Pastrana

2021

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

Deep Learning (DL) is a powerful solution for complex problems in many disciplines such as finance, medical research, or social sciences. Due to the high computational cost of DL algorithms, data scientists often rely upon Machine Learning as a Service (MLaaS) to outsource the computation onto third-party servers. However, outsourcing the computation raises privacy concerns when dealing with sensitive information, e.g., health or financial records. Also, privacy regulations like the European GDPR limit the collection, distribution, and use of such sensitive data. Recent advances in privacy-preserving computation techniques (i.e., Homomorphic Encryption and Secure Multiparty Computation) have enabled DL training and inference over protected data. However, these techniques are still immature and difficult to deploy in practical scenarios. In this work, we review the evolution of the adaptation of privacy-preserving computation techniques onto DL, to understand the gap between research proposals and practical applications. We highlight the relative advantages and disadvantages, considering aspects such as efficiency shortcomings, reproducibility issues due to the lack of standard tools and programming interfaces, or lack of integration with DL frameworks commonly used by the data science community.

show abstract

“…One example is [242], in which a proof is provided for Yao's two-party functionality computing protocol [417], under semi-honest security assumption. A stricter assumption is the malicious attack assumption, where each participated party may not follow the protocol and take any possible measures to infer the data [241]. Covert adversaries assumption is proposed in [33], where the involved parties may be malicious but they do not wish to be "caught" attacking the computation.…”

Section: Privacy Protectionmentioning

confidence: 99%

Trustworthy AI: From Principles to Practices

Li¹,

Pan²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fast developing artificial intelligence (AI) technology has enabled various applied systems deployed in the real world, impacting people's everyday lives. However, many current AI systems were found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection, etc., which not only degrades user experience but erodes the society's trust in all AI systems. In this review, we strive to provide AI practitioners a comprehensive guide towards building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, alignment with human values, and accountability. We then survey leading approaches in these aspects in the industry. To unify the current fragmented approaches towards trustworthy AI, we propose a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items to practitioners and societal stakeholders (e.g., researchers and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges in the future development of trustworthy AI systems, where we identify the need for paradigm shift towards comprehensive trustworthy AI systems.

show abstract

Secure multiparty computation

Abstract: MPC has moved from theoretical study to real-world usage. How is it doing?

Cited by 102 publications

References 37 publications

Privacy-preserving dataset combination and Lasso regression for healthcare predictions

Privacy-preserving dataset combination and Lasso regression for healthcare predictions

SoK: Privacy-Preserving Computation Techniques for Deep Learning

Trustworthy AI: From Principles to Practices

Contact Info

Product

Resources

About