Matches in SemOpenAlex for { <https://semopenalex.org/work/W2799803467> ?p ?o ?g. }
- W2799803467 abstract "Collaborative machine learning and related techniques such as distributed and federated learning allow multiple participants, each with his own training dataset, to build a joint model. Participants train local models and periodically exchange model parameters or gradient updates computed during the training. We demonstrate that the training data used by participants in collaborative learning is vulnerable to inference attacks. First, we show that an adversarial participant can infer the presence of exact data points in others' training data (i.e., membership inference). Then, we demonstrate that the adversary can infer properties that hold only for a subset of the training data and are independent of the properties that the joint model aims to capture. We evaluate the efficacy of our attacks on a variety of tasks, datasets, and learning configurations, and conclude with a discussion of possible defenses." @default.
- W2799803467 created "2018-05-17" @default.
- W2799803467 creator A5027364160 @default.
- W2799803467 creator A5035799220 @default.
- W2799803467 creator A5038206174 @default.
- W2799803467 creator A5048446895 @default.
- W2799803467 date "2018-05-10" @default.
- W2799803467 modified "2023-09-26" @default.
- W2799803467 title "Inference Attacks Against Collaborative Learning." @default.
- W2799803467 cites W1165382972 @default.
- W2799803467 cites W1442374986 @default.
- W2799803467 cites W1473189865 @default.
- W2799803467 cites W1782590233 @default.
- W2799803467 cites W1930624869 @default.
- W2799803467 cites W2024922353 @default.
- W2799803467 cites W2040228409 @default.
- W2799803467 cites W2051267297 @default.
- W2799803467 cites W2053637704 @default.
- W2799803467 cites W2076063813 @default.
- W2799803467 cites W2095705004 @default.
- W2799803467 cites W2099471712 @default.
- W2799803467 cites W2101234009 @default.
- W2799803467 cites W2106313770 @default.
- W2799803467 cites W2110287632 @default.
- W2799803467 cites W2166706236 @default.
- W2799803467 cites W2168231600 @default.
- W2799803467 cites W2186615578 @default.
- W2799803467 cites W2187089797 @default.
- W2799803467 cites W2198253679 @default.
- W2799803467 cites W2198403777 @default.
- W2799803467 cites W2252024402 @default.
- W2799803467 cites W2263253503 @default.
- W2799803467 cites W2283463896 @default.
- W2799803467 cites W2329660289 @default.
- W2799803467 cites W2461943168 @default.
- W2799803467 cites W2513128224 @default.
- W2799803467 cites W2529995663 @default.
- W2799803467 cites W2535690855 @default.
- W2799803467 cites W2541884796 @default.
- W2799803467 cites W2544902556 @default.
- W2799803467 cites W2579247884 @default.
- W2799803467 cites W2608764892 @default.
- W2799803467 cites W2630997112 @default.
- W2799803467 cites W2701059868 @default.
- W2799803467 cites W2766255512 @default.
- W2799803467 cites W2767079719 @default.
- W2799803467 cites W2777914285 @default.
- W2799803467 cites W2785361959 @default.
- W2799803467 cites W2786233556 @default.
- W2799803467 cites W2786943863 @default.
- W2799803467 cites W2787698406 @default.
- W2799803467 cites W2788502731 @default.
- W2799803467 cites W2795435272 @default.
- W2799803467 cites W2884280357 @default.
- W2799803467 cites W2887995258 @default.
- W2799803467 cites W2897830718 @default.
- W2799803467 cites W2919115771 @default.
- W2799803467 cites W2949338291 @default.
- W2799803467 cites W2949492662 @default.
- W2799803467 cites W2949541494 @default.
- W2799803467 cites W2950404409 @default.
- W2799803467 cites W2950602864 @default.
- W2799803467 cites W2950635152 @default.
- W2799803467 cites W2951055356 @default.
- W2799803467 cites W2951368041 @default.
- W2799803467 cites W2962835266 @default.
- W2799803467 cites W2962835968 @default.
- W2799803467 cites W2963053914 @default.
- W2799803467 cites W2963803379 @default.
- W2799803467 cites W2964151798 @default.
- W2799803467 cites W2965267010 @default.
- W2799803467 cites W574900623 @default.
- W2799803467 cites W2777097994 @default.
- W2799803467 hasPublicationYear "2018" @default.
- W2799803467 type Work @default.
- W2799803467 sameAs 2799803467 @default.
- W2799803467 citedByCount "46" @default.
- W2799803467 countsByYear W27998034672017 @default.
- W2799803467 countsByYear W27998034672018 @default.
- W2799803467 countsByYear W27998034672019 @default.
- W2799803467 countsByYear W27998034672020 @default.
- W2799803467 countsByYear W27998034672021 @default.
- W2799803467 crossrefType "posted-content" @default.
- W2799803467 hasAuthorship W2799803467A5027364160 @default.
- W2799803467 hasAuthorship W2799803467A5035799220 @default.
- W2799803467 hasAuthorship W2799803467A5038206174 @default.
- W2799803467 hasAuthorship W2799803467A5048446895 @default.
- W2799803467 hasConcept C119857082 @default.
- W2799803467 hasConcept C121332964 @default.
- W2799803467 hasConcept C127413603 @default.
- W2799803467 hasConcept C136197465 @default.
- W2799803467 hasConcept C153294291 @default.
- W2799803467 hasConcept C154945302 @default.
- W2799803467 hasConcept C170154142 @default.
- W2799803467 hasConcept C18555067 @default.
- W2799803467 hasConcept C2776214188 @default.
- W2799803467 hasConcept C2777211547 @default.
- W2799803467 hasConcept C2992525071 @default.
- W2799803467 hasConcept C37736160 @default.
- W2799803467 hasConcept C38652104 @default.