Secure Federated Submodel Learning
Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server. However, the conventional framework requires each client to leverage the full model for learning, which can be prohibitively inefficient for resource-constrained clients and large-scale deep learning tasks. We thus propose a new framework, called federated submodel learning, where clients download only the needed parts of the full model, namely submodels, and then upload the submodel updates. Nevertheless, the "position" of a client's truly required submodel corresponds to her private data, and its disclosure to the cloud server during interactions inevitably breaks the tenet of federated learning. To integrate efficiency and privacy, we have designed a secure federated submodel learning scheme coupled with a private set union protocol as a cornerstone. Our secure scheme features the properties of randomized response, secure aggregation, and Bloom filter, and endows each client with a customized plausible deniability, in terms of local differential privacy, against the position of her desired submodel, thus protecting her private data. We further instantiated our scheme with the e-commerce recommendation scenario in Alibaba, implemented a prototype system, and extensively evaluated its performance over 30-day Taobao user data. The analysis and evaluation results demonstrate the feasibility and scalability of our scheme from model accuracy and convergency, practical communication, computation, and storage overheads, as well as manifest its remarkable advantages over the conventional federated learning framework.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Chaoyue Niu (edit)
Fan Wu (edit)
Shaojie Tang (add twitter)
Lifeng Hua (add twitter)
Rongfei Jia (add twitter)
Chengfei Lv (add twitter)
Zhihua Wu (add twitter)
Guihai Chen (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
11/06/19 06:03PM
29,220
4,860
Tweets
LanternInst: Secure Federated Submodel Learning #ArtificialIntelligence #Secure #ai via https://t.co/jnJxWgplgl https://t.co/NO6aOVZxVs
arxiv_cs_LG: Secure Federated Submodel Learning. Chaoyue Niu, Fan Wu, Shaojie Tang, Lifeng Hua, Rongfei Jia, Chengfei Lv, Zhihua Wu, and Guihai Chen https://t.co/gOrpKnvyxY
Apollonaught1: RT @Nicochan33: Secure Federated Submodel Learning #ArtificialIntelligence #Secure #ai https://t.co/eTqr93OHSP
SogatecniaI: Secure Federated Submodel Learning #ArtificialIntelligence #Secure #ai via https://t.co/dk0caya0Oh https://t.co/lcqNLB0mME
arxivml: "Secure Federated Submodel Learning", Chaoyue Niu, Fan Wu, Shaojie Tang, Lifeng Hua, Rongfei Jia, Chengfei Lv, Zhih… https://t.co/xy3kQwE9JG
Aijobs_com: Secure Federated Submodel Learning #ArtificialIntelligence #Secure #ai via https://t.co/qObPsEDIzA https://t.co/I0Y2PTFT0W
SciFi: Secure Federated Submodel Learning. https://t.co/MSSuv9cOb7
amruthasuri: Secure Federated Submodel Learning #ArtificialIntelligence #Secure #ai via https://t.co/gydENhzRSg https://t.co/OPfvIVc8M1
BrundageBot: Secure Federated Submodel Learning. Chaoyue Niu, Fan Wu, Shaojie Tang, Lifeng Hua, Rongfei Jia, Chengfei Lv, Zhihua Wu, and Guihai Chen https://t.co/Fscqg2Rf2x
Nicochan33: Secure Federated Submodel Learning #ArtificialIntelligence #Secure #ai https://t.co/eTqr93OHSP
aiglobal4: Secure Federated Submodel Learning #ArtificialIntelligence #Secure #ai via https://t.co/mj7vYUA5y6 https://t.co/xXV31thyEO
Images
Related