Privacy-preserving matrix factorization

By Valeria Nikolaenko, Stratis Ioannidis, Udi Weinsberg, Marc Joye, Nina Taft, Dan Boneh. 2013

305 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Privacy & Security

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 Representation & Self-Supervised Learning

In Privacy & Security

Citations in the corpus

QUOTIENT: Two-Party Secure Neural Network Training and Prediction (2019, methodology): “These trade-offs lead to a natural idea recently exploited in several works in the secure computation for ML: one should design protocols that are customized to full algorithms, such as the training of linear/logistic regressors and DNNs [14, 41, 44], matrix factorization [43], or k-nearest neighbor”
Prio: Private, Robust, and Scalable Computation of Aggregate Statistics (2017, background): “, exact max), and some special-case MPC protocols [5, 29, 96] are practical today for certain applications.”
Contamination Attacks and Mitigation in Multi-Party Machine Learning (2018, neutral): “Secure MPC can be enabled with cryptographic techniques [6, 11, 18, 29, 32], and systems based on trusted processors such as Intel SGX [3, 5, 33].”
Crypto-Nets: Neural Networks over Encrypted Data (2014, methodology): “…studied how to do HE-based privacy-preserving training or prediction of linear regression (Nikolaenko et al., 2013b; Wu & Haven, 2012), linear classiﬁers (Bos et al., 2014; Bost et al., 2014; Graepel et al., 2013), decision trees (Bost et al., 2014), matrix factorization (Nikolaenko et al., 2013a).”
Efficient Private Statistics with Succinct Sketches (2015, methodology): “Homomorphic encryption based techniques have also been used to perform other machine learning operations on encrypted data, including matrix factorization [56], linear classi-ﬁers [11, 40], and decision trees [12].”
Blind Justice: Fairness with Encrypted Sensitive Attributes (2018, methodology): “(cid:104) (cid:105) (cid:104) (cid:105) The idea of privately outsourcing computation to two non-colluding parties in this way is recurrent in MPC, and often referred to as the two-server model (Mohassel & Zhang, 2017; Gasc´on et al., 2017; Nikolaenko et al., 2013b; Al-Rubaie et al., 2017).”
Secure Function Evaluation Using an FPGA Overlay Architecture (2017, background): “, over threads [28] or across a cluster of machines [27].”
ABY - A Framework for Efficient Mixed-Protocol Secure Two-Party Computation (2015, methodology): “Mixed-protocols have been used for several privacy-preserving applications, such as medical diagnostics [3], fingerprint recognition [39], iris- and fingercode authentication [10], ridge-regression [60], computation on non-integers and Hidden Markov Models [31], and matrix factorization [59].”
A Pragmatic Introduction to Secure Multi-Party Computation (2019, methodology): “Several works have developed customized protocols for particular tasks that combine homomorphic encryption with generic MPC (Brickell et al., 2007; Huang et al., 2011c; Nikolaenko et al., 2013a; Nikolaenko et al., 2013b).”
GraphSC: Parallel Secure Computation Made Easy (2015, background): “In this work, we follow the second approach to enable parallel oblivious versions for a range of data mining algorithms.”
Oblivious Multi-Party Machine Learning on Trusted Processors (2016, methodology): “, Nursery in [13], MovieLens in [47, 48]) or because they are one of the”
A Simple and Efficient Federated Recommender System (2019, methodology): “Among the extensive research to secure privacy in recommender systems are methods that include cryptography algorithms [7, 23] and differential privacy [4, 20].”
Practical Privacy Preserving POI Recommendation (2020, methodology): “The second type is based on cryptography techniques such as homomorphic encryption [23] and secure Multi-Party Computation (MPC) [62], and typical methods include Refs [2], [6], [20], [42], and [44].”
Towards a More Reliable Privacy-preserving Recommender System (2017, background): “without Additional Information without 3rd Party Existence Protected Model Protected Value Protected [5] √ √ √ √ [13] √ √ √ √ [14] √ √ √ [10] √ √ √ [7] √ √ √ [11] √ √ √”
DStress: Efficient Differentially Private Computations on Distributed Data (2017, background): “Recently, work on two-party secure computation (2PC) has started considering graph computations as well [55, 56].”
Secure Federated Matrix Factorization (2019, methodology): “Moreover, if the crypto-service provider collude with the recommendation server, then no user privacy protection can be preserved [Kim et al. , 2016; Nikolaenko et al. , 2013].”
Cryptϵ: Crypto-Assisted Differential Privacy on Untrusted Servers (2019, methodology): “for privacy preserving machine learning approaches where one of the servers manages the cryptographic primitives while the other handles computation [46, 48, 67, 80, 83, 84].”