Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386496237> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4386496237 endingPage "156" @default.
- W4386496237 startingPage "147" @default.
- W4386496237 abstract "Federated learning (FL) has been widely used in IoT applications. However, FL is vulnerable to various attacks in its each phase. Existing defense in federated learning mainly focus on the centralized setting. And centralized parameter-server settings require a trusted third party to collect and distribute model parameters. However, the requirement of a trusted third party cannot always be satisfied in many cases. Meanwhile, the centralized settings suffer from the inherent vulnerability of single-point-of-failure (SPOF), in which the whole system cease to function once the parameter server is broken. Therefore, decentralized federated learning has gain great attention recently. Existing conventional defence strategies are mostly designed for the centralized parameter-server architecture. The problem is that these conventional defence strategies cannot cope with new challenges occurred in highly decentralized settings of FL. Firstly, in a trustless setting, malicious participants can cause breakdown to the whole system on the communication level by disrupting model exchanges. Secondly, current defensive methods cannot effectively identify and rule out malicious participants. In either case, a harmful bias hurts the performance even if malicious participants do not perform model-level attacks. Therefore, defensive strategies for the decentralized-manner FL are in urgent need. To this end, we propose a committee-based FL system, named ComAvg, under a trustless setting. ComAvg provides a general coordination scheme for robust aggregation of distributed learning. With reliability assessment scheme to expel abnormal participants and fortified classic model exchange methods, the conventional centralized methods of FL can be easily modified into decentralized versions to cope with the two challenges aforementioned. Finally, we implement a prototype of ComAvg and perform various groups of evaluations on its robustness. The prototype-based evaluation results and theoretical analysis show that the proposed ComAvg is effective against model attacks such as sign-flipping and communication-level isolating attacks." @default.
- W4386496237 created "2023-09-07" @default.
- W4386496237 creator A5000582109 @default.
- W4386496237 creator A5008167844 @default.
- W4386496237 creator A5025290467 @default.
- W4386496237 creator A5044264564 @default.
- W4386496237 creator A5047931252 @default.
- W4386496237 date "2023-11-01" @default.
- W4386496237 modified "2023-10-16" @default.
- W4386496237 title "ComAvg: Robust decentralized federated learning with random committees" @default.
- W4386496237 cites W1966383354 @default.
- W4386496237 cites W2007661053 @default.
- W4386496237 cites W2443267493 @default.
- W4386496237 cites W2535104337 @default.
- W4386496237 cites W3090464427 @default.
- W4386496237 cites W3137092842 @default.
- W4386496237 doi "https://doi.org/10.1016/j.comcom.2023.09.004" @default.
- W4386496237 hasPublicationYear "2023" @default.
- W4386496237 type Work @default.
- W4386496237 citedByCount "0" @default.
- W4386496237 crossrefType "journal-article" @default.
- W4386496237 hasAuthorship W4386496237A5000582109 @default.
- W4386496237 hasAuthorship W4386496237A5008167844 @default.
- W4386496237 hasAuthorship W4386496237A5025290467 @default.
- W4386496237 hasAuthorship W4386496237A5044264564 @default.
- W4386496237 hasAuthorship W4386496237A5047931252 @default.
- W4386496237 hasConcept C120314980 @default.
- W4386496237 hasConcept C121332964 @default.
- W4386496237 hasConcept C123657996 @default.
- W4386496237 hasConcept C134306372 @default.
- W4386496237 hasConcept C14036430 @default.
- W4386496237 hasConcept C142362112 @default.
- W4386496237 hasConcept C153349607 @default.
- W4386496237 hasConcept C163258240 @default.
- W4386496237 hasConcept C165136773 @default.
- W4386496237 hasConcept C2992525071 @default.
- W4386496237 hasConcept C33923547 @default.
- W4386496237 hasConcept C38652104 @default.
- W4386496237 hasConcept C41008148 @default.
- W4386496237 hasConcept C43214815 @default.
- W4386496237 hasConcept C62520636 @default.
- W4386496237 hasConcept C77618280 @default.
- W4386496237 hasConcept C78458016 @default.
- W4386496237 hasConcept C86803240 @default.
- W4386496237 hasConcept C95713431 @default.
- W4386496237 hasConceptScore W4386496237C120314980 @default.
- W4386496237 hasConceptScore W4386496237C121332964 @default.
- W4386496237 hasConceptScore W4386496237C123657996 @default.
- W4386496237 hasConceptScore W4386496237C134306372 @default.
- W4386496237 hasConceptScore W4386496237C14036430 @default.
- W4386496237 hasConceptScore W4386496237C142362112 @default.
- W4386496237 hasConceptScore W4386496237C153349607 @default.
- W4386496237 hasConceptScore W4386496237C163258240 @default.
- W4386496237 hasConceptScore W4386496237C165136773 @default.
- W4386496237 hasConceptScore W4386496237C2992525071 @default.
- W4386496237 hasConceptScore W4386496237C33923547 @default.
- W4386496237 hasConceptScore W4386496237C38652104 @default.
- W4386496237 hasConceptScore W4386496237C41008148 @default.
- W4386496237 hasConceptScore W4386496237C43214815 @default.
- W4386496237 hasConceptScore W4386496237C62520636 @default.
- W4386496237 hasConceptScore W4386496237C77618280 @default.
- W4386496237 hasConceptScore W4386496237C78458016 @default.
- W4386496237 hasConceptScore W4386496237C86803240 @default.
- W4386496237 hasConceptScore W4386496237C95713431 @default.
- W4386496237 hasFunder F4320336405 @default.
- W4386496237 hasLocation W43864962371 @default.
- W4386496237 hasOpenAccess W4386496237 @default.
- W4386496237 hasPrimaryLocation W43864962371 @default.
- W4386496237 hasRelatedWork W1485627940 @default.
- W4386496237 hasRelatedWork W1521353230 @default.
- W4386496237 hasRelatedWork W1596201972 @default.
- W4386496237 hasRelatedWork W1596397513 @default.
- W4386496237 hasRelatedWork W1986253068 @default.
- W4386496237 hasRelatedWork W2152433827 @default.
- W4386496237 hasRelatedWork W2160425906 @default.
- W4386496237 hasRelatedWork W2385146268 @default.
- W4386496237 hasRelatedWork W3096015116 @default.
- W4386496237 hasRelatedWork W4322730952 @default.
- W4386496237 hasVolume "211" @default.
- W4386496237 isParatext "false" @default.
- W4386496237 isRetracted "false" @default.
- W4386496237 workType "article" @default.