BASS: Blockchain-Based Asynchronous SignSGD for Robust Collaborative Data Mining

Xu, C; Qu, Y; Xiang, Y; Gao, L; Smith, D; Yu, S

BASS: Blockchain-Based Asynchronous SignSGD for Robust Collaborative Data Mining

Xu, C Qu, Y Xiang, Y Gao, L Smith, D Yu, S

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA), 2023, 00, pp. 1-7
Issue Date:: 2023-02-08

Closed Access

	Filename	Description	Size
	BASS_Blockchain-Based_Asynchronous_SignSGD_for_Robust_Collaborative_Data_Mining.pdf	Published version	1.72 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Xu, C
dc.contributor.author	Qu, Y
dc.contributor.author	Xiang, Y
dc.contributor.author	Gao, L
dc.contributor.author	Smith, D
dc.contributor.author	Yu, S https://orcid.org/0000-0003-4485-6743
dc.date	2022-10-13
dc.date.accessioned	2023-05-09T02:08:57Z
dc.date.available	2023-05-09T02:08:57Z
dc.date.issued	2023-02-08
dc.identifier.citation	2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA), 2023, 00, pp. 1-7
dc.identifier.isbn	9781665473309
dc.identifier.uri	http://hdl.handle.net/10453/170288
dc.description.abstract	Federated learning (FL) is a machine learning framework for collaborative data mining in many scenarios (e.g. Internet of Things) due to its privacy-preserving feature. However, various attacks arise security concerns of FL, such as poisoning, backdoor, and DDoS attacks. Several blockchain-based FL schemes strengthen credibility and security without considering the increased communication overhead. Some existing work compresses local updated gradients to sign vectors to lower communication overhead at the expense of model accuracy. To address the above concerns, this paper offers a blockchain-based asynchronous SignSGD (BASS) scheme. A novel asynchronous sign aggregation algorithm is introduced to ensure model accuracy even if the local updated gradients are compressed to sign vectors. Considering the unstable network connection on IoT, a consensus algorithm that elects multiple leader nodes enables reliable global model aggregation. The introduced blockchain improves credibility and security without downgrading efficiency. Empirical studies show that BASS outperforms other schemes in efficiency, model accuracy, and security.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA)
dc.relation.ispartof	2022 IEEE 9th International Conference on Data Science and Advanced Analytics
dc.relation.isbasedon	10.1109/dsaa54385.2022.10032341
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	BASS: Blockchain-Based Asynchronous SignSGD for Robust Collaborative Data Mining
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Shenzhen, China
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CCSP - Centre for Cyber Security and Privacy
utslib.copyright.status	closed_access	*
dc.date.updated	2023-05-09T02:08:56Z
pubs.finish-date	2022-10-16
pubs.publication-status	Published
pubs.start-date	2022-10-13
pubs.volume	00

Abstract:

Federated learning (FL) is a machine learning framework for collaborative data mining in many scenarios (e.g. Internet of Things) due to its privacy-preserving feature. However, various attacks arise security concerns of FL, such as poisoning, backdoor, and DDoS attacks. Several blockchain-based FL schemes strengthen credibility and security without considering the increased communication overhead. Some existing work compresses local updated gradients to sign vectors to lower communication overhead at the expense of model accuracy. To address the above concerns, this paper offers a blockchain-based asynchronous SignSGD (BASS) scheme. A novel asynchronous sign aggregation algorithm is introduced to ensure model accuracy even if the local updated gradients are compressed to sign vectors. Considering the unstable network connection on IoT, a consensus algorithm that elects multiple leader nodes enables reliable global model aggregation. The introduced blockchain improves credibility and security without downgrading efficiency. Empirical studies show that BASS outperforms other schemes in efficiency, model accuracy, and security.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/170288