A Blockchain-Enabled Federated Learning Model for Privacy Preservation: System Design

被引：24

作者：

Qi, Minfeng ^{[1
]}

Wang, Ziyuan ^{[1
]}

Wu, Fan ^{[1
]}

Hanson, Rob ^{[2
]}

Chen, Shiping ^{[2
]}

Xiang, Yang ^{[1
]}

Zhu, Liming ^{[2
]}

机构：

[1] Swinburne Univ Technol, Melbourne, Vic, Australia

[2] CSIRO Data61, Sydney, NSW, Australia

来源：

INFORMATION SECURITY AND PRIVACY, ACISP 2021 | 2021年 / 13083卷

关键词：

Blockchain; Smart contract; Homomorphic encryption; Federated learning; Privacy protection; Data sharing;

D O I：

10.1007/978-3-030-90567-5_24

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Information Silo is a common problem in most industries, while Federated Learning (FL) as an emerging privacy-preservation technique aims to facilitate data sharing to solve the problem. It avoids data leakage by sharing the model gradient instead of the raw data. However, there are some challenges of FL, such as Single Point of Failure (SPoF), gradient privacy, and trust issues. This paper proposes a Homomorphic-integrated and blockchain-based FL model to address the above issues. It provides gradient privacy protection by employing Homomorphic, and uses a smart contract-based reputation scheme and an on/off-chain storage strategy to respectively solve FL trust and blockchain storage issues. In the end, it evaluates the proposed model by providing a qualitative privacy analysis and conducting preliminary experiments on model performance.

引用

页码：473 / 489

页数：17

共 29 条

[11]

Ethereum, 2013, NEXT GENERATION SMAR

[12]

European Union (EU), 2018, GEN DAT PROT REG GDP

[13] A Survey of Homomorphic Encryption for Nonspecialists [J].

Fontaine, Caroline ;

Galand, Fabien .

EURASIP JOURNAL ON INFORMATION SECURITY, 2007, (01)

[14] Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning [J].

Hitaj, Briland ;

Ateniese, Giuseppe ;

Perez-Cruz, Fernando .

CCS'17: PROCEEDINGS OF THE 2017 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2017, :603-618

[15]

Kairouz P., 2019, arXiv preprint arXiv:1912.04977

[16] Deep Video Portraits [J].

Kim, Hyeongwoo ;

Garrido, Pablo ;

Tewari, Ayush ;

Xu, Weipeng ;

Thies, Justus ;

Niessner, Matthias ;

Perez, Patrick ;

Richardt, Christian ;

Zollhofer, Michael ;

Theobalt, Christian .

ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (04)

[17]

Learn S., 2020, DIAB DAT

[18] Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT [J].

Lu, Yunlong ;

Huang, Xiaohong ;

Dai, Yueyue ;

Maharjan, Sabita ;

Zhang, Yan .

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020, 16 (06) :4177-4186

[19]

Lyu L., 2019, arXiv preprint arXiv:1906.01167, P1

[20] Record and Reward Federated Learning Contributions with Blockchain [J].

Martinez, Ismael ;

Francis, Sreya ;

Hafid, Abdelhakim Senhaji .

2019 INTERNATIONAL CONFERENCE ON CYBER-ENABLED DISTRIBUTED COMPUTING AND KNOWLEDGE DISCOVERY (CYBERC), 2019, :50-57

← 1 2 3 →