Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285121820> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4285121820 endingPage "21983" @default.
- W4285121820 startingPage "21971" @default.
- W4285121820 abstract "Federated learning (FL) has emerged to leverage datasets from multiple devices to improve the performance of a machine learning (ML) model while providing privacy preservation for devices. The training data is collected at the devices, also known as FL workers, which collaboratively train a global learning model and share their local model updates with a central entity or server without sharing their data. However, FL can be susceptible to various adversarial attacks that target its security and privacy. In particular, the workers can upload unreliable local model updates, leading to corruption of the main FL task. Workers may intentionally contribute unreliable local updates by launching poisoning attacks or unintentionally by updating low-quality models caused by high device mobility, limited device resources, or unstable network connection. Consequently, identifying reliable and trustworthy workers becomes critical for FL security. In this article, the concept of reputation is adopted as a metric to evaluate workers’ reliability and trustworthiness. In addition, deep reinforcement learning (DRL)-based reputation mechanism is proposed for optimal selection and evaluation of reliable FL workers. Due to the dynamic nature of worker behavior in the FL environment, the DRL-based algorithm deep deterministic policy gradient (DDPG) is employed to improve the FL model accuracy and stability. We compare the performance of our proposed method with a conventional reputation method and deep <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$Q$ </tex-math></inline-formula> -networks (DQNs)-based reputation method. Our simulation results demonstrate that our proposed method can improve FL accuracy by more than 30% under various scenarios and achieves better convergence than the other methods." @default.
- W4285121820 created "2022-07-14" @default.
- W4285121820 creator A5037234286 @default.
- W4285121820 creator A5048637322 @default.
- W4285121820 creator A5071309872 @default.
- W4285121820 creator A5088133457 @default.
- W4285121820 date "2022-11-01" @default.
- W4285121820 modified "2023-09-27" @default.
- W4285121820 title "Toward Secure Federated Learning for IoT Using DRL-Enabled Reputation Mechanism" @default.
- W4285121820 doi "https://doi.org/10.1109/jiot.2022.3184812" @default.
- W4285121820 hasPublicationYear "2022" @default.
- W4285121820 type Work @default.
- W4285121820 citedByCount "1" @default.
- W4285121820 countsByYear W42851218202023 @default.
- W4285121820 crossrefType "journal-article" @default.
- W4285121820 hasAuthorship W4285121820A5037234286 @default.
- W4285121820 hasAuthorship W4285121820A5048637322 @default.
- W4285121820 hasAuthorship W4285121820A5071309872 @default.
- W4285121820 hasAuthorship W4285121820A5088133457 @default.
- W4285121820 hasConcept C119857082 @default.
- W4285121820 hasConcept C136764020 @default.
- W4285121820 hasConcept C144024400 @default.
- W4285121820 hasConcept C153083717 @default.
- W4285121820 hasConcept C154945302 @default.
- W4285121820 hasConcept C36289849 @default.
- W4285121820 hasConcept C38652104 @default.
- W4285121820 hasConcept C41008148 @default.
- W4285121820 hasConcept C48798503 @default.
- W4285121820 hasConcept C71901391 @default.
- W4285121820 hasConcept C97541855 @default.
- W4285121820 hasConceptScore W4285121820C119857082 @default.
- W4285121820 hasConceptScore W4285121820C136764020 @default.
- W4285121820 hasConceptScore W4285121820C144024400 @default.
- W4285121820 hasConceptScore W4285121820C153083717 @default.
- W4285121820 hasConceptScore W4285121820C154945302 @default.
- W4285121820 hasConceptScore W4285121820C36289849 @default.
- W4285121820 hasConceptScore W4285121820C38652104 @default.
- W4285121820 hasConceptScore W4285121820C41008148 @default.
- W4285121820 hasConceptScore W4285121820C48798503 @default.
- W4285121820 hasConceptScore W4285121820C71901391 @default.
- W4285121820 hasConceptScore W4285121820C97541855 @default.
- W4285121820 hasFunder F4320332753 @default.
- W4285121820 hasIssue "21" @default.
- W4285121820 hasLocation W42851218201 @default.
- W4285121820 hasOpenAccess W4285121820 @default.
- W4285121820 hasPrimaryLocation W42851218201 @default.
- W4285121820 hasRelatedWork W1983811306 @default.
- W4285121820 hasRelatedWork W2007535360 @default.
- W4285121820 hasRelatedWork W2365093105 @default.
- W4285121820 hasRelatedWork W2372117511 @default.
- W4285121820 hasRelatedWork W3022038857 @default.
- W4285121820 hasRelatedWork W3170628611 @default.
- W4285121820 hasRelatedWork W3203000071 @default.
- W4285121820 hasRelatedWork W4307308173 @default.
- W4285121820 hasRelatedWork W4318719223 @default.
- W4285121820 hasRelatedWork W4319083788 @default.
- W4285121820 hasVolume "9" @default.
- W4285121820 isParatext "false" @default.
- W4285121820 isRetracted "false" @default.
- W4285121820 workType "article" @default.