<div class="csl-bib-body">
<div class="csl-entry">Kieseberg, P., Weippl, E., Tjoa, A. M., Cabitza, F., Campagner, A., & Holzinger, A. (2023). Controllable AI - An Alternative to Trustworthiness in Complex AI Systems? In A. Holzinger, P. Kieseberg, & F. Cabitza (Eds.), <i>Machine Learning and Knowledge Extraction : 7th IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2023, Benevento, Italy, August 29 – September 1, 2023, Proceedings</i> (pp. 1–12). Springer. https://doi.org/10.1007/978-3-031-40837-3_1</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/192764
-
dc.description.abstract
The release of ChatGPT to the general public has sparked discussions about the dangers of artificial intelligence (AI) among the public. The European Commission’s draft of the AI Act has further fueled these discussions, particularly in relation to the definition of AI and the assignment of risk levels to different technologies. Security concerns in AI systems arise from the need to protect against potential adversaries and to safeguard individuals from AI decisions that may harm their well-being. However, ensuring secure and trustworthy AI systems is challenging, especially with deep learning models that lack explainability. This paper proposes the concept of Controllable AI as an alternative to Trustworthy AI and explores the major differences between the two. The aim is to initiate discussions on securing complex AI systems without sacrificing practical capabilities or transparency. The paper provides an overview of techniques that can be employed to achieve Controllable AI. It discusses the background definitions of explainability, Trustworthy AI, and the AI Act. The principles and techniques of Controllable AI are detailed, including detecting and managing control loss, implementing transparent AI decisions, and addressing intentional bias or backdoors. The paper concludes by discussing the potential applications of Controllable AI and its implications for real-world scenarios.
en
dc.language.iso
en
-
dc.relation.ispartofseries
Lecture Notes in Computer Science
-
dc.subject
Artificial Intelligence
en
dc.subject
Digital Transformation
en
dc.subject
Trustworthy AI
en
dc.subject
AI risks
en
dc.subject
AI threats
en
dc.title
Controllable AI - An Alternative to Trustworthiness in Complex AI Systems?
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.contributor.affiliation
St. Pölten University of Applied Sciences, Austria
-
dc.contributor.affiliation
SBA Research, Austria
-
dc.contributor.affiliation
University of Milano-Bicocca, Italy
-
dc.contributor.affiliation
University of Milano-Bicocca, Italy
-
dc.contributor.affiliation
Medical University of Graz, Austria
-
dc.relation.isbn
978-3-031-40837-3
-
dc.description.startpage
1
-
dc.description.endpage
12
-
dc.type.category
Full-Paper Contribution
-
tuw.booktitle
Machine Learning and Knowledge Extraction : 7th IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2023, Benevento, Italy, August 29 – September 1, 2023, Proceedings
-
tuw.container.volume
14065
-
tuw.relation.publisher
Springer
-
tuw.relation.publisherplace
Cham
-
tuw.researchTopic.id
I4
-
tuw.researchTopic.name
Information Systems Engineering
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E194-04 - Forschungsbereich Data Science
-
tuw.publication.orgunit
E194-01 - Forschungsbereich Software Engineering
-
tuw.publisher.doi
10.1007/978-3-031-40837-3_1
-
dc.description.numberOfPages
12
-
tuw.author.orcid
0000-0002-2847-2152
-
tuw.author.orcid
0000-0002-8295-9252
-
tuw.author.orcid
0000-0002-4065-3415
-
tuw.author.orcid
0000-0002-0027-5157
-
tuw.author.orcid
0000-0002-6786-5194
-
tuw.editor.orcid
0000-0002-6786-5194
-
tuw.editor.orcid
0000-0002-2847-2152
-
tuw.editor.orcid
0000-0002-4065-3415
-
tuw.event.name
International Cross-Domain Conference for Machine Learning and Knowledge Extraction, CD-MAKE 2023
en
tuw.event.startdate
29-08-2023
-
tuw.event.enddate
01-09-2023
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Benevento
-
tuw.event.country
IT
-
tuw.event.presenter
Kieseberg, Peter
-
wb.sciencebranch
Informatik
-
wb.sciencebranch
Wirtschaftswissenschaften
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.oefos
5020
-
wb.sciencebranch.value
90
-
wb.sciencebranch.value
10
-
item.fulltext
no Fulltext
-
item.openairetype
conference paper
-
item.languageiso639-1
en
-
item.grantfulltext
none
-
item.openairecristype
http://purl.org/coar/resource_type/c_5794
-
item.cerifentitytype
Publications
-
crisitem.author.dept
St. P�lten University of Applied Sciences
-
crisitem.author.dept
E194-01 - Forschungsbereich Software Engineering
-
crisitem.author.dept
E194-04 - Forschungsbereich Data Science
-
crisitem.author.dept
University of Milano-Bicocca
-
crisitem.author.dept
University of Milano-Bicocca
-
crisitem.author.dept
E192 - Institut für Logic and Computation
-
crisitem.author.orcid
0000-0002-2847-2152
-
crisitem.author.orcid
0000-0002-8295-9252
-
crisitem.author.orcid
0000-0002-4065-3415
-
crisitem.author.orcid
0000-0002-6786-5194
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering