Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201824817> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3201824817 endingPage "496" @default.
- W3201824817 startingPage "476" @default.
- W3201824817 abstract "Training a deep neural network requires substantial data and intensive computing resources. Unaffordable price holds back many potential applications of deep learning. Besides, it is risky to gather user’s private data for training centrally. Then federated learning appears as a promising solution to having users learned jointly while keeping training data local. However, security issues keep coming up in federated learning applications. One of the most threatening attacks is the model poisoning attack which can manipulate the inference result of a jointly learned model. Some recent studies show that elaborate model poisoning approaches can even breach the existing Byzantine-robust federated learning solutions. Hence, it is critical to discuss alternative solutions to secure federated learning. In this paper, we propose to protect federated learning against model poisoning attacks by introducing a robust model aggregation solution named Romoa. Unlike previous studies, Romoa can deal with targeted and untargeted poisoning attacks with a unified approach. Moreover, Romoa achieves more precise attack detection and better fairness for federated learning participants by constructing a new similarity measurement. We conclude that through a comprehensive evaluation of standard datasets, Romoa can provide a satisfying defense effect against model poisoning attacks, including those attacks breaching Byzantine-robust federated learning solutions." @default.
- W3201824817 created "2021-10-11" @default.
- W3201824817 creator A5021621535 @default.
- W3201824817 creator A5026169204 @default.
- W3201824817 creator A5053766627 @default.
- W3201824817 creator A5086254999 @default.
- W3201824817 date "2021-01-01" @default.
- W3201824817 modified "2023-09-30" @default.
- W3201824817 title "Romoa: Robust Model Aggregation for the Resistance of Federated Learning to Model Poisoning Attacks" @default.
- W3201824817 cites W2053637704 @default.
- W3201824817 cites W2112796928 @default.
- W3201824817 cites W2164500538 @default.
- W3201824817 cites W2767079719 @default.
- W3201824817 cites W2789471414 @default.
- W3201824817 cites W2930926105 @default.
- W3201824817 cites W2962763344 @default.
- W3201824817 cites W2982302101 @default.
- W3201824817 cites W2997547170 @default.
- W3201824817 cites W3034389259 @default.
- W3201824817 cites W3087391814 @default.
- W3201824817 cites W3096328345 @default.
- W3201824817 cites W3106416029 @default.
- W3201824817 cites W3119520312 @default.
- W3201824817 cites W3138597937 @default.
- W3201824817 doi "https://doi.org/10.1007/978-3-030-88418-5_23" @default.
- W3201824817 hasPublicationYear "2021" @default.
- W3201824817 type Work @default.
- W3201824817 sameAs 3201824817 @default.
- W3201824817 citedByCount "9" @default.
- W3201824817 countsByYear W32018248172022 @default.
- W3201824817 countsByYear W32018248172023 @default.
- W3201824817 crossrefType "book-chapter" @default.
- W3201824817 hasAuthorship W3201824817A5021621535 @default.
- W3201824817 hasAuthorship W3201824817A5026169204 @default.
- W3201824817 hasAuthorship W3201824817A5053766627 @default.
- W3201824817 hasAuthorship W3201824817A5086254999 @default.
- W3201824817 hasConcept C103278499 @default.
- W3201824817 hasConcept C108583219 @default.
- W3201824817 hasConcept C115961682 @default.
- W3201824817 hasConcept C119857082 @default.
- W3201824817 hasConcept C154945302 @default.
- W3201824817 hasConcept C2776214188 @default.
- W3201824817 hasConcept C2984842247 @default.
- W3201824817 hasConcept C2992525071 @default.
- W3201824817 hasConcept C38652104 @default.
- W3201824817 hasConcept C41008148 @default.
- W3201824817 hasConceptScore W3201824817C103278499 @default.
- W3201824817 hasConceptScore W3201824817C108583219 @default.
- W3201824817 hasConceptScore W3201824817C115961682 @default.
- W3201824817 hasConceptScore W3201824817C119857082 @default.
- W3201824817 hasConceptScore W3201824817C154945302 @default.
- W3201824817 hasConceptScore W3201824817C2776214188 @default.
- W3201824817 hasConceptScore W3201824817C2984842247 @default.
- W3201824817 hasConceptScore W3201824817C2992525071 @default.
- W3201824817 hasConceptScore W3201824817C38652104 @default.
- W3201824817 hasConceptScore W3201824817C41008148 @default.
- W3201824817 hasLocation W32018248171 @default.
- W3201824817 hasOpenAccess W3201824817 @default.
- W3201824817 hasPrimaryLocation W32018248171 @default.
- W3201824817 hasRelatedWork W2795261237 @default.
- W3201824817 hasRelatedWork W3014300295 @default.
- W3201824817 hasRelatedWork W3164822677 @default.
- W3201824817 hasRelatedWork W4223943233 @default.
- W3201824817 hasRelatedWork W4225161397 @default.
- W3201824817 hasRelatedWork W4312200629 @default.
- W3201824817 hasRelatedWork W4360585206 @default.
- W3201824817 hasRelatedWork W4364306694 @default.
- W3201824817 hasRelatedWork W4380075502 @default.
- W3201824817 hasRelatedWork W4380086463 @default.
- W3201824817 isParatext "false" @default.
- W3201824817 isRetracted "false" @default.
- W3201824817 magId "3201824817" @default.
- W3201824817 workType "book-chapter" @default.