FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3028543371> ?p ?o ?g. }

• W3028543371 abstract "In this paper, we address the problem of privacy-preserving distributed learning and evaluation of machine learning models by analyzing it in the widespread MapReduce abstraction that we extend with privacy constraints. Following this abstraction, we instantiate SPINDLE (Scalable Privacy-preservINg Distributed LEarning), an operational distributed system that supports the privacy-preserving training and evaluation of generalized linear models on distributed datasets. SPINDLE enables the efficient execution of distributed gradient descent while ensuring data and model confidentiality, as long as at least one of the data providers is honest-but-curious. The trained model is then used for oblivious predictions on confidential data. SPINDLE is able to efficiently perform demanding training tasks that require a high number of iterations on large input data with thousands of features, distributed among hundreds of data providers. It relies on a multiparty homomorphic encryption scheme to execute high-depth computations on encrypted data without significant overhead. It further leverages on its distributed construction and the packing capabilities of the cryptographic scheme to efficiently parallelize the computations at multiple levels. In our evaluation, SPINDLE performs the training of a logistic-regression model on a dataset of one million samples with 32 features distributed among 160 data providers in less than 176 seconds, yielding similar accuracy to non-secure centralized models." @default.
• W3028543371 created "2020-05-29" @default.
• W3028543371 creator A5000583679 @default.
• W3028543371 creator A5025665736 @default.
• W3028543371 creator A5031281762 @default.
• W3028543371 creator A5072336168 @default.
• W3028543371 creator A5080497445 @default.
• W3028543371 creator A5089763199 @default.
• W3028543371 creator A5091369772 @default.
• W3028543371 date "2020-05-19" @default.
• W3028543371 modified "2023-09-28" @default.
• W3028543371 title "Scalable Privacy-Preserving Distributed Learning" @default.
• W3028543371 cites W133884053 @default.
• W3028543371 cites W1617663512 @default.
• W3028543371 cites W1971991172 @default.
• W3028543371 cites W2031738616 @default.
• W3028543371 cites W2032775418 @default.
• W3028543371 cites W2037037409 @default.
• W3028543371 cites W2051267297 @default.
• W3028543371 cites W2053637704 @default.
• W3028543371 cites W2088492763 @default.
• W3028543371 cites W2091825929 @default.
• W3028543371 cites W2098290658 @default.
• W3028543371 cites W2106970188 @default.
• W3028543371 cites W2108834246 @default.
• W3028543371 cites W2109722477 @default.
• W3028543371 cites W2110287632 @default.
• W3028543371 cites W2112380340 @default.
• W3028543371 cites W2129713986 @default.
• W3028543371 cites W2132172731 @default.
• W3028543371 cites W2141420453 @default.
• W3028543371 cites W2164278908 @default.
• W3028543371 cites W2167732364 @default.
• W3028543371 cites W2168231600 @default.
• W3028543371 cites W2173213060 @default.
• W3028543371 cites W2221443338 @default.
• W3028543371 cites W2233194383 @default.
• W3028543371 cites W2283463896 @default.
• W3028543371 cites W2295292576 @default.
• W3028543371 cites W236632755 @default.
• W3028543371 cites W2400124473 @default.
• W3028543371 cites W2400700555 @default.
• W3028543371 cites W2402235285 @default.
• W3028543371 cites W2435473771 @default.
• W3028543371 cites W2470666398 @default.
• W3028543371 cites W2473418344 @default.
• W3028543371 cites W2530417694 @default.
• W3028543371 cites W2535690855 @default.
• W3028543371 cites W2541884796 @default.
• W3028543371 cites W2557283755 @default.
• W3028543371 cites W2575671591 @default.
• W3028543371 cites W2587454507 @default.
• W3028543371 cites W2588978745 @default.
• W3028543371 cites W2591882872 @default.
• W3028543371 cites W2620512600 @default.
• W3028543371 cites W2701059868 @default.
• W3028543371 cites W2729599932 @default.
• W3028543371 cites W2744999500 @default.
• W3028543371 cites W2747433492 @default.
• W3028543371 cites W2758259983 @default.
• W3028543371 cites W2765200655 @default.
• W3028543371 cites W2766831133 @default.
• W3028543371 cites W2768174108 @default.
• W3028543371 cites W2777638777 @default.
• W3028543371 cites W2781091734 @default.
• W3028543371 cites W2784621220 @default.
• W3028543371 cites W278760476 @default.
• W3028543371 cites W2789894922 @default.
• W3028543371 cites W2793675838 @default.
• W3028543371 cites W2795097198 @default.
• W3028543371 cites W2800453812 @default.
• W3028543371 cites W2800679800 @default.
• W3028543371 cites W2801490189 @default.
• W3028543371 cites W2801491268 @default.
• W3028543371 cites W2801958627 @default.
• W3028543371 cites W2802758511 @default.
• W3028543371 cites W2811248283 @default.
• W3028543371 cites W2883074043 @default.
• W3028543371 cites W2891866930 @default.
• W3028543371 cites W2894604724 @default.
• W3028543371 cites W2894784988 @default.
• W3028543371 cites W2895782209 @default.
• W3028543371 cites W2895865029 @default.
• W3028543371 cites W2896684650 @default.
• W3028543371 cites W2896938420 @default.
• W3028543371 cites W2898108725 @default.
• W3028543371 cites W2899771611 @default.
• W3028543371 cites W2899790086 @default.
• W3028543371 cites W2951264056 @default.
• W3028543371 cites W2952061910 @default.
• W3028543371 cites W2954442424 @default.
• W3028543371 cites W2955023110 @default.
• W3028543371 cites W2962867198 @default.
• W3028543371 cites W2963106566 @default.
• W3028543371 cites W2963433607 @default.
• W3028543371 cites W2963456518 @default.
• W3028543371 cites W2963733194 @default.
• W3028543371 cites W2963752132 @default.
• W3028543371 cites W2963804082 @default.
• W3028543371 cites W2964162474 @default.

• next