Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Providing assurance and scrutability on shared data and machine learning models with verifiable credentials

Barclay, Iain, Preece, Alun ORCID: https://orcid.org/0000-0003-0349-9057, Taylor, Ian ORCID: https://orcid.org/0000-0001-5040-0772, Radha, Swapna Krishnakumar and Nabrzyski, Jarek 2022. Providing assurance and scrutability on shared data and machine learning models with verifiable credentials. Concurrency and Computation: Practice and Experience , e6997. 10.1002/cpe.6997

Full text not available from this repository.

Abstract

Adopting shared data resources requires scientists to place trust in the originators of the data. When shared data is later used in the development of artificial intelligence (AI) systems or machine learning (ML) models, the trust lineage extends to the users of the system, typically practitioners in fields such as healthcare and finance. Practitioners rely on AI developers to have used relevant, trustworthy data, but may have limited insight and recourse. This article introduces a software architecture and implementation of a system based on design patterns from the field of self-sovereign identity. Scientists can issue signed credentials attesting to qualities of their data resources. Data contributions to ML models are recorded in a bill of materials (BOM), which is stored with the model as a verifiable credential. The BOM provides a traceable record of the supply chain for an AI system, which facilitates on-going scrutiny of the qualities of the contributing components. The verified BOM, and its linkage to certified data qualities, is used in the AI scrutineer, a web-based tool designed to offer practitioners insight into ML model constituents and highlight any problems with adopted datasets, should they be found to have biased data or be otherwise discredited.

Item Type: Article
Date Type: Published Online
Status: In Press
Schools: Computer Science & Informatics
Publisher: Wiley
ISSN: 1532-0626
Date of Acceptance: 16 March 2022
Last Modified: 10 Nov 2022 11:12
URI: https://orca.cardiff.ac.uk/id/eprint/149668

Actions (repository staff only)

Edit Item Edit Item