Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383221569> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4383221569 abstract "Federated Learning (FL) is a machine learning technique that enables multiple parties to collaboratively train a model using their private datasets. Given its decentralized nature, FL has inherent vulnerabilities that make it susceptible to adversarial attacks. The success of an attack on FL depends upon several (latent) factors, including the adversary’s strength, the chosen attack strategy, and the effectiveness of the defense measures in place. There is a growing body of literature on empirical attack studies on FL, but no systematic way to compare and evaluate the completeness of these studies, which raises questions about their validity. To address this problem, we introduce a causal model that captures the relationship between the different (latent) factors, and their reflexive indicators, that can impact the success of an attack on FL. The proposed model, inspired by structural equation modeling, helps systematize the existing literature on FL attack studies and provides a way to compare and contrast their completeness. We validate the model and demonstrate its utility through experimental evaluation of select attack studies. Our aim is to help researchers in the FL domain design more complete attack studies and improve the understanding of FL vulnerabilities." @default.
- W4383221569 created "2023-07-06" @default.
- W4383221569 creator A5000678710 @default.
- W4383221569 creator A5055776740 @default.
- W4383221569 creator A5063038462 @default.
- W4383221569 creator A5063839073 @default.
- W4383221569 date "2023-07-10" @default.
- W4383221569 modified "2023-10-07" @default.
- W4383221569 title "SoK: Systematizing Attack Studies in Federated Learning – From Sparseness to Completeness" @default.
- W4383221569 cites W2930926105 @default.
- W4383221569 cites W2963456518 @default.
- W4383221569 cites W2995191368 @default.
- W4383221569 cites W3033686777 @default.
- W4383221569 cites W3084847664 @default.
- W4383221569 cites W3091870957 @default.
- W4383221569 cites W3097210233 @default.
- W4383221569 cites W3103802018 @default.
- W4383221569 cites W3136620885 @default.
- W4383221569 cites W3138153888 @default.
- W4383221569 cites W3138198612 @default.
- W4383221569 cites W3157850870 @default.
- W4383221569 cites W3167500796 @default.
- W4383221569 cites W3203932036 @default.
- W4383221569 cites W4207073300 @default.
- W4383221569 cites W4210630464 @default.
- W4383221569 cites W4213110664 @default.
- W4383221569 cites W4220928404 @default.
- W4383221569 cites W4224316323 @default.
- W4383221569 cites W4226493408 @default.
- W4383221569 cites W4229455429 @default.
- W4383221569 cites W4280575929 @default.
- W4383221569 cites W4288057793 @default.
- W4383221569 cites W4300991139 @default.
- W4383221569 doi "https://doi.org/10.1145/3579856.3590328" @default.
- W4383221569 hasPublicationYear "2023" @default.
- W4383221569 type Work @default.
- W4383221569 citedByCount "0" @default.
- W4383221569 crossrefType "proceedings-article" @default.
- W4383221569 hasAuthorship W4383221569A5000678710 @default.
- W4383221569 hasAuthorship W4383221569A5055776740 @default.
- W4383221569 hasAuthorship W4383221569A5063038462 @default.
- W4383221569 hasAuthorship W4383221569A5063839073 @default.
- W4383221569 hasConcept C119857082 @default.
- W4383221569 hasConcept C134306372 @default.
- W4383221569 hasConcept C154945302 @default.
- W4383221569 hasConcept C165696696 @default.
- W4383221569 hasConcept C17231256 @default.
- W4383221569 hasConcept C2776502983 @default.
- W4383221569 hasConcept C33923547 @default.
- W4383221569 hasConcept C37736160 @default.
- W4383221569 hasConcept C38652104 @default.
- W4383221569 hasConcept C41008148 @default.
- W4383221569 hasConcept C41065033 @default.
- W4383221569 hasConcept C65856478 @default.
- W4383221569 hasConceptScore W4383221569C119857082 @default.
- W4383221569 hasConceptScore W4383221569C134306372 @default.
- W4383221569 hasConceptScore W4383221569C154945302 @default.
- W4383221569 hasConceptScore W4383221569C165696696 @default.
- W4383221569 hasConceptScore W4383221569C17231256 @default.
- W4383221569 hasConceptScore W4383221569C2776502983 @default.
- W4383221569 hasConceptScore W4383221569C33923547 @default.
- W4383221569 hasConceptScore W4383221569C37736160 @default.
- W4383221569 hasConceptScore W4383221569C38652104 @default.
- W4383221569 hasConceptScore W4383221569C41008148 @default.
- W4383221569 hasConceptScore W4383221569C41065033 @default.
- W4383221569 hasConceptScore W4383221569C65856478 @default.
- W4383221569 hasLocation W43832215691 @default.
- W4383221569 hasOpenAccess W4383221569 @default.
- W4383221569 hasPrimaryLocation W43832215691 @default.
- W4383221569 hasRelatedWork W286553814 @default.
- W4383221569 hasRelatedWork W2898291644 @default.
- W4383221569 hasRelatedWork W2963456518 @default.
- W4383221569 hasRelatedWork W3124408655 @default.
- W4383221569 hasRelatedWork W3204946594 @default.
- W4383221569 hasRelatedWork W4297785512 @default.
- W4383221569 hasRelatedWork W4297845793 @default.
- W4383221569 hasRelatedWork W4311711335 @default.
- W4383221569 hasRelatedWork W4362599004 @default.
- W4383221569 hasRelatedWork W4379255972 @default.
- W4383221569 isParatext "false" @default.
- W4383221569 isRetracted "false" @default.
- W4383221569 workType "article" @default.