Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033686777> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3033686777 endingPage "2444" @default.
- W3033686777 startingPage "2430" @default.
- W3033686777 abstract "Federated learning has emerged as an advanced privacy-preserving learning technique for mobile edge computing, where the model is trained in a decentralized manner by the clients, preventing the server from directly accessing those private data from the clients. This learning mechanism significantly challenges the attack from the server side. Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i.e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client. To analyze the privacy leakage of federated learning, this paper gives the first attempt to explore user-level privacy leakage by the attack from a malicious server. We propose a framework incorporating GAN with a multi-task discriminator, called multi-task GAN - Auxiliary Identification (mGAN-AI), which simultaneously discriminates category, reality, and client identity of input samples. The novel discrimination on client identity enables the generator to recover user specified private data. Unlike existing works interfering the federated learning process, the proposed method works “invisibly” on the server side. Furthermore, considering the anonymization strategy for mitigating mGAN-AI, we propose a beforehand linkability attack which re-identifies the anonymized updates by associating the client representatives. A novel siamese network fusing the identification and verification models is developed for measuring the similarity of representatives. The experimental results demonstrate the effectiveness of the proposed approaches and the superior to the state-of-the-art." @default.
- W3033686777 created "2020-06-12" @default.
- W3033686777 creator A5013726931 @default.
- W3033686777 creator A5015419107 @default.
- W3033686777 creator A5025482368 @default.
- W3033686777 creator A5046225712 @default.
- W3033686777 creator A5065058975 @default.
- W3033686777 creator A5072730926 @default.
- W3033686777 creator A5085556383 @default.
- W3033686777 date "2020-10-01" @default.
- W3033686777 modified "2023-10-16" @default.
- W3033686777 title "Analyzing User-Level Privacy Attack Against Federated Learning" @default.
- W3033686777 cites W1915485278 @default.
- W3033686777 cites W2051267297 @default.
- W3033686777 cites W2103560185 @default.
- W3033686777 cites W2103647628 @default.
- W3033686777 cites W2535690855 @default.
- W3033686777 cites W2591882872 @default.
- W3033686777 cites W2630997112 @default.
- W3033686777 cites W2701059868 @default.
- W3033686777 cites W2767079719 @default.
- W3033686777 cites W2781091734 @default.
- W3033686777 cites W2887995258 @default.
- W3033686777 cites W2930926105 @default.
- W3033686777 cites W2963456518 @default.
- W3033686777 cites W2964162474 @default.
- W3033686777 cites W2966579212 @default.
- W3033686777 cites W2971544778 @default.
- W3033686777 cites W2975069432 @default.
- W3033686777 cites W2986305485 @default.
- W3033686777 cites W2989885118 @default.
- W3033686777 cites W3004589439 @default.
- W3033686777 cites W3098711604 @default.
- W3033686777 cites W4205228770 @default.
- W3033686777 cites W955924517 @default.
- W3033686777 doi "https://doi.org/10.1109/jsac.2020.3000372" @default.
- W3033686777 hasPublicationYear "2020" @default.
- W3033686777 type Work @default.
- W3033686777 sameAs 3033686777 @default.
- W3033686777 citedByCount "104" @default.
- W3033686777 countsByYear W30336867772020 @default.
- W3033686777 countsByYear W30336867772021 @default.
- W3033686777 countsByYear W30336867772022 @default.
- W3033686777 countsByYear W30336867772023 @default.
- W3033686777 crossrefType "journal-article" @default.
- W3033686777 hasAuthorship W3033686777A5013726931 @default.
- W3033686777 hasAuthorship W3033686777A5015419107 @default.
- W3033686777 hasAuthorship W3033686777A5025482368 @default.
- W3033686777 hasAuthorship W3033686777A5046225712 @default.
- W3033686777 hasAuthorship W3033686777A5065058975 @default.
- W3033686777 hasAuthorship W3033686777A5072730926 @default.
- W3033686777 hasAuthorship W3033686777A5085556383 @default.
- W3033686777 hasConcept C119857082 @default.
- W3033686777 hasConcept C123201435 @default.
- W3033686777 hasConcept C154945302 @default.
- W3033686777 hasConcept C2779803651 @default.
- W3033686777 hasConcept C31258907 @default.
- W3033686777 hasConcept C37736160 @default.
- W3033686777 hasConcept C38652104 @default.
- W3033686777 hasConcept C41008148 @default.
- W3033686777 hasConcept C76155785 @default.
- W3033686777 hasConcept C93996380 @default.
- W3033686777 hasConcept C94915269 @default.
- W3033686777 hasConceptScore W3033686777C119857082 @default.
- W3033686777 hasConceptScore W3033686777C123201435 @default.
- W3033686777 hasConceptScore W3033686777C154945302 @default.
- W3033686777 hasConceptScore W3033686777C2779803651 @default.
- W3033686777 hasConceptScore W3033686777C31258907 @default.
- W3033686777 hasConceptScore W3033686777C37736160 @default.
- W3033686777 hasConceptScore W3033686777C38652104 @default.
- W3033686777 hasConceptScore W3033686777C41008148 @default.
- W3033686777 hasConceptScore W3033686777C76155785 @default.
- W3033686777 hasConceptScore W3033686777C93996380 @default.
- W3033686777 hasConceptScore W3033686777C94915269 @default.
- W3033686777 hasFunder F4320321001 @default.
- W3033686777 hasFunder F4320322186 @default.
- W3033686777 hasFunder F4320335777 @default.
- W3033686777 hasFunder F4320335787 @default.
- W3033686777 hasIssue "10" @default.
- W3033686777 hasLocation W30336867771 @default.
- W3033686777 hasOpenAccess W3033686777 @default.
- W3033686777 hasPrimaryLocation W30336867771 @default.
- W3033686777 hasRelatedWork W121432690 @default.
- W3033686777 hasRelatedWork W2952541330 @default.
- W3033686777 hasRelatedWork W2962992635 @default.
- W3033686777 hasRelatedWork W2995777218 @default.
- W3033686777 hasRelatedWork W3059450896 @default.
- W3033686777 hasRelatedWork W3092429552 @default.
- W3033686777 hasRelatedWork W4280544492 @default.
- W3033686777 hasRelatedWork W4312845401 @default.
- W3033686777 hasRelatedWork W4364305485 @default.
- W3033686777 hasRelatedWork W4379255972 @default.
- W3033686777 hasVolume "38" @default.
- W3033686777 isParatext "false" @default.
- W3033686777 isRetracted "false" @default.
- W3033686777 magId "3033686777" @default.
- W3033686777 workType "article" @default.