2021
DOI: 10.1155/2021/5534270
|View full text |Cite
|
Sign up to set email alerts
|

User‐Level Membership Inference for Federated Learning in Wireless Network Environment

Abstract: With the rise of privacy concerns in traditional centralized machine learning services, federated learning, which incorporates multiple participants to train a global model across their localized training data, has lately received significant attention in both industry and academia. Bringing federated learning into a wireless network scenario is a great move. The combination of them inspires tremendous power and spawns a number of promising applications. Recent researches reveal the inherent vulnerabilities of… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
2
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 29 publications
(31 reference statements)
0
2
0
Order By: Relevance
“…Then, many works took further steps to study more fine-grained membership inference attacks, e.g. [12,26,30,36,49]. However, existing membership inference attacks cannot be used in FedRec because of the major differences mentioned in Section 1.…”
Section: Attack Against Federated Learningmentioning
confidence: 99%
See 1 more Smart Citation
“…Then, many works took further steps to study more fine-grained membership inference attacks, e.g. [12,26,30,36,49]. However, existing membership inference attacks cannot be used in FedRec because of the major differences mentioned in Section 1.…”
Section: Attack Against Federated Learningmentioning
confidence: 99%
“…Inferring a user's interaction data in FedRecs is one type of membership inference attack (MIA). Although MIA has been widely investigated in federated classification tasks [4,21,25,30,43,49], their proposed attack and defense approaches cannot apply to Fe-dRecs due to the following major differences between federated recommendation and federated classification. (1) From the perspective of attack objective, MIA in federated classification aims to infer or predict whether a sample has been used in the federated training process and which client has used it for the local training.…”
Section: Introductionmentioning
confidence: 99%