Secure Multiparty Computation

By Keith B. Frikken. 2011

661 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

Privacy‐preserving federated learning based on multi‐key homomorphic encryption (2021, positive): “Since homomorphic multiplication is not involved in our federated learning mechanism, we introduce the additive homomorphism of MK-CKKS only.”
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, background): “Cryptographic methods such as homomorphic encryption [13], [26], [66], [108], [143], and secure multi-party computation (SMC) [20], [21], [30], [152] are widely used in privacy-preserving machine learning algorithms.”
Emerging technologies towards enhancing privacy in genomic data sharing (2019, background): “For example, secure multiparty computation (MPC) frameworks [6] allow multiple entities (e.”
Trustworthy AI: From Principles to Practices (2021, background): “A stricter assumption is the malicious attack assumption, where each participating party need not follow the given protocol, and can take any possible measure to infer the data [214].”
PrivEdge: From Local to Distributed Private Training and Prediction (2020, methodology): “For these reasons, MPC techniques are used for private prediction [44]–[47], but the cost of communication between parties remains as a major bottleneck.”
Towards Demystifying Membership Inference Attacks (2018, background): “This divergence separates membership inference from existing areas of privacy research, such as differential privacy [4], [43], [14] or secure multiparty computation [44], [10], [9].”
HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning (2019, background): “SMC allows multiple parties to compute a function over their inputs, without revealing their individual inputs [5, 10].”
On the Power of Multiple Anonymous Messages (2019, neutral): “…queries, then there is a rich theory, within cryptography, of secure multi-party computation (SMPC) that allows f p x 1 , . . . , x n q to be computed without revealing anything about x i except what can be inferred from f p x 1 , . . . , x n q itself (see, e.g., the book of Cramer et al. [39]).”
Security and Privacy Challenges of Large Language Models: A Survey (2024, neutral): “Secure multi-party computation [221] can be another way to defend against privacy attacks in LLMs, which can be explored in future research.”
Private Heavy Hitters and Range Queries in the Shuffled Model (2019, background): “…the computation of each query q , then there is a rich theory of secure multi-party computation (SMPC) that allows f p x 1 , . . . , x n q to be computed without revealing anything about x i except what can be inferred from f p x 1 , . . . , x n q itself (see e.g., the book of Cramer et al. [21]).”
Demystifying Membership Inference Attacks in Machine Learning as a Service (2019, neutral): “This divergence separates membership inference from existing areas of privacy research, such as differential privacy [11], [12], [13] or secure multiparty computation [14], [15], [16].”