Leveraging Knowledge Graphs for AI System Auditing and Transparency

Auditing complex Artificial Intelligence (AI) systems is gaining importance in light of new regulations and is particularly challenging in terms of system complexity, knowledge integration, and differing transparency needs. Current AI auditing tools however, lack semantic context, resulting in diffi...

Full description

Saved in:
Bibliographic Details
Main Authors: Laura Waltersdorfer, Marta Sabou
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Web Semantics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1570826824000350
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841545621277769728
author Laura Waltersdorfer
Marta Sabou
author_facet Laura Waltersdorfer
Marta Sabou
author_sort Laura Waltersdorfer
collection DOAJ
description Auditing complex Artificial Intelligence (AI) systems is gaining importance in light of new regulations and is particularly challenging in terms of system complexity, knowledge integration, and differing transparency needs. Current AI auditing tools however, lack semantic context, resulting in difficulties for auditors in effectively collecting and integrating, but also for analysing and querying audit data. In this position paper, we explore how Knowledge Graphs (KGs) can address these challenges by offering a structured and integrative approach to collecting and transforming audit traces. This work discusses the current limitations in both AI auditing processes and tools. Furthermore, we examine how KGs can play a transformative role in overcoming these obstacles to achieve improved auditability and transparency of AI systems.
format Article
id doaj-art-ede1d1f3f0e148c1bf7e73516a2c8020
institution Kabale University
issn 1570-8268
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Web Semantics
spelling doaj-art-ede1d1f3f0e148c1bf7e73516a2c80202025-01-12T05:24:30ZengElsevierWeb Semantics1570-82682025-01-0184100849Leveraging Knowledge Graphs for AI System Auditing and TransparencyLaura Waltersdorfer0Marta Sabou1Vienna University of Economics and Business (WU), Welthandelsplatz 1, Vienna, 1020, Austria; Technische Universität Wien (TU), Favoritenstraße 9-11, Vienna, 1040, Austria; Corresponding author.Vienna University of Economics and Business (WU), Welthandelsplatz 1, Vienna, 1020, AustriaAuditing complex Artificial Intelligence (AI) systems is gaining importance in light of new regulations and is particularly challenging in terms of system complexity, knowledge integration, and differing transparency needs. Current AI auditing tools however, lack semantic context, resulting in difficulties for auditors in effectively collecting and integrating, but also for analysing and querying audit data. In this position paper, we explore how Knowledge Graphs (KGs) can address these challenges by offering a structured and integrative approach to collecting and transforming audit traces. This work discusses the current limitations in both AI auditing processes and tools. Furthermore, we examine how KGs can play a transformative role in overcoming these obstacles to achieve improved auditability and transparency of AI systems.http://www.sciencedirect.com/science/article/pii/S1570826824000350AI auditingKnowledge GraphsAI transparency
spellingShingle Laura Waltersdorfer
Marta Sabou
Leveraging Knowledge Graphs for AI System Auditing and Transparency
Web Semantics
AI auditing
Knowledge Graphs
AI transparency
title Leveraging Knowledge Graphs for AI System Auditing and Transparency
title_full Leveraging Knowledge Graphs for AI System Auditing and Transparency
title_fullStr Leveraging Knowledge Graphs for AI System Auditing and Transparency
title_full_unstemmed Leveraging Knowledge Graphs for AI System Auditing and Transparency
title_short Leveraging Knowledge Graphs for AI System Auditing and Transparency
title_sort leveraging knowledge graphs for ai system auditing and transparency
topic AI auditing
Knowledge Graphs
AI transparency
url http://www.sciencedirect.com/science/article/pii/S1570826824000350
work_keys_str_mv AT laurawaltersdorfer leveragingknowledgegraphsforaisystemauditingandtransparency
AT martasabou leveragingknowledgegraphsforaisystemauditingandtransparency