Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361859148> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W4361859148 abstract "Federated learning (FL) is a privacy-preserving distributed machine learning architecture to solve the problem of data silos. While FL is proposed to protect data security, it still faces security challenges. Backdoor attacks are potential threats in FL and aim to manipulate the model performance on chosen backdoor tasks by injecting adversarial triggers. As a more insidious variant of backdoor attacks, distributed backdoor attacks decompose the same global trigger into multiple local patterns and respectively assign them to different attackers. In this paper, we study deep into the entire training process of current distributed backdoor attack (DBA) and propose a cooperative DBA method for non-IID FL to break through existing defenses. To bypass the cosine similarity detection, we design an update rotation and scaling technique based on two independent training to well disguise malicious updates among benign updates. We conduct an exhaustive experiment to evaluate the performance of our proposed method under the state-of-the-art defenses. The experimental results show that it is much more stealthy than the current DBA method while maintaining the high backdoor attack intensity." @default.
- W4361859148 created "2023-04-05" @default.
- W4361859148 creator A5055970384 @default.
- W4361859148 creator A5065355770 @default.
- W4361859148 creator A5072546950 @default.
- W4361859148 date "2022-12-01" @default.
- W4361859148 modified "2023-10-16" @default.
- W4361859148 title "Breaking Distributed Backdoor Defenses for Federated Learning in Non-IID Settings" @default.
- W4361859148 cites W151377110 @default.
- W4361859148 cites W2934843808 @default.
- W4361859148 cites W2966689772 @default.
- W4361859148 cites W2982302101 @default.
- W4361859148 cites W2990270730 @default.
- W4361859148 cites W3004155269 @default.
- W4361859148 cites W3091870957 @default.
- W4361859148 cites W3204548896 @default.
- W4361859148 doi "https://doi.org/10.1109/msn57253.2022.00064" @default.
- W4361859148 hasPublicationYear "2022" @default.
- W4361859148 type Work @default.
- W4361859148 citedByCount "0" @default.
- W4361859148 crossrefType "proceedings-article" @default.
- W4361859148 hasAuthorship W4361859148A5055970384 @default.
- W4361859148 hasAuthorship W4361859148A5065355770 @default.
- W4361859148 hasAuthorship W4361859148A5072546950 @default.
- W4361859148 hasConcept C111919701 @default.
- W4361859148 hasConcept C149810388 @default.
- W4361859148 hasConcept C154945302 @default.
- W4361859148 hasConcept C162324750 @default.
- W4361859148 hasConcept C2781045450 @default.
- W4361859148 hasConcept C37736160 @default.
- W4361859148 hasConcept C38652104 @default.
- W4361859148 hasConcept C41008148 @default.
- W4361859148 hasConcept C50522688 @default.
- W4361859148 hasConcept C98045186 @default.
- W4361859148 hasConceptScore W4361859148C111919701 @default.
- W4361859148 hasConceptScore W4361859148C149810388 @default.
- W4361859148 hasConceptScore W4361859148C154945302 @default.
- W4361859148 hasConceptScore W4361859148C162324750 @default.
- W4361859148 hasConceptScore W4361859148C2781045450 @default.
- W4361859148 hasConceptScore W4361859148C37736160 @default.
- W4361859148 hasConceptScore W4361859148C38652104 @default.
- W4361859148 hasConceptScore W4361859148C41008148 @default.
- W4361859148 hasConceptScore W4361859148C50522688 @default.
- W4361859148 hasConceptScore W4361859148C98045186 @default.
- W4361859148 hasLocation W43618591481 @default.
- W4361859148 hasOpenAccess W4361859148 @default.
- W4361859148 hasPrimaryLocation W43618591481 @default.
- W4361859148 hasRelatedWork W3124800868 @default.
- W4361859148 hasRelatedWork W3127875616 @default.
- W4361859148 hasRelatedWork W3178326529 @default.
- W4361859148 hasRelatedWork W4210410860 @default.
- W4361859148 hasRelatedWork W4225857837 @default.
- W4361859148 hasRelatedWork W4288391221 @default.
- W4361859148 hasRelatedWork W4289435389 @default.
- W4361859148 hasRelatedWork W4297791914 @default.
- W4361859148 hasRelatedWork W4319050247 @default.
- W4361859148 hasRelatedWork W3037549549 @default.
- W4361859148 isParatext "false" @default.
- W4361859148 isRetracted "false" @default.
- W4361859148 workType "article" @default.