A Semantic Framework to Support AI System Accountability and Audit

Iman Naja, Milan Markovic, Pete Edwards, Caitlin Cottrill

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

8 Citations (Scopus)
9 Downloads (Pure)


To realise accountable AI systems, different types of information from a range of sources need to be recorded throughout the system life cycle. We argue that knowledge graphs may support capture and audit of such information; however, the creation of such accountability records must be planned and embedded within different life cycle stages, e.g., during the design of a system, during implementation, etc. We propose a provenance based approach to support not only the capture of accountability information, but also abstract descriptions of accountability plans that guide the data collection process, all as part of a single knowledge graph. In this paper we introduce the SAO ontology, a lightweight generic ontology for describing accountability plans and corresponding provenance traces of computational systems; the RAInS ontology, which extends SAO to model accountability information relevant to the design stage of AI systems; and a proof-of-concept implementation utilising the proposed ontologies to provide a visual interface for designing accountability plans, and managing accountability records.
Original languageEnglish
Title of host publicationThe Semantic Web. ESWC 2021. Lecture Notes in Computer Science
PublisherSpringer Nature Switzerland AG
Number of pages17
ISBN (Electronic)978-3-030-77385-4
ISBN (Print)978-3-030-77384-7
Publication statusPublished - 6 Jun 2021
Event18th European Semantic Web Conference, ESWC 2021 - Online , Hersonissos, Greece
Duration: 6 Jun 202110 Jun 2021


Workshop18th European Semantic Web Conference, ESWC 2021
Internet address


  • AI
  • Provenance
  • Accountability
  • Ontology


Dive into the research topics of 'A Semantic Framework to Support AI System Accountability and Audit'. Together they form a unique fingerprint.

Cite this