Abstract | ||
---|---|---|
Privacy-preserving multi-party machine learning allows multiple organizations to perform collaborative data analytics while guaranteeing the privacy of their individual datasets. Using trusted SGX-processors for this task yields high performance, but requires a careful selection, adaptation, and implementation of machine-learning algorithms to provably prevent the exploitation of any side channels induced by data-dependent access patterns.We propose data-oblivious machine learning algorithms for support vector machines, matrix factorization, neural networks, decision trees, and k-means clustering. We show that our efficient implementation based on Intel Skylake processors scales up to large, realistic datasets, with overheads several orders of magnitude lower than with previous approaches based on advanced cryptographic multi-party computation schemes. |
Year | Venue | Field |
---|---|---|
2016 | PROCEEDINGS OF THE 25TH USENIX SECURITY SYMPOSIUM | Decision tree,Data analysis,Computer science,Cryptography,Support vector machine,Matrix decomposition,Theoretical computer science,Direct Anonymous Attestation,Artificial neural network,Cluster analysis |
DocType | Citations | PageRank |
Conference | 39 | 1.02 |
References | Authors | |
47 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Olga Ohrimenko | 1 | 494 | 27.48 |
Felix Schuster | 2 | 413 | 12.47 |
Cédric Fournet | 3 | 3698 | 213.79 |
Aastha Mehta | 4 | 39 | 1.02 |
Sebastian Nowozin | 5 | 2104 | 90.05 |
Kapil Vaswani | 6 | 685 | 30.29 |
Manuel Costa | 7 | 1589 | 88.62 |