umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour
Umeå University.ORCID iD: 0000-0002-8423-8029
Umeå University.ORCID iD: 0000-0001-9499-1535
Umeå University.
Umeå University.ORCID iD: 0000-0001-7409-5813
2019 (English)In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019Conference paper, Published paper (Other academic)
Abstract [en]

Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains which directly affect human well-being. However, if AI is to improve people’s lives, then people must be able to trust it, by being able to understand what the system is doing and why. Although transparency is often seen as the requirementin this case, realistically it might not always be possible, whereas the need to ensure that the system operates within set moral bounds remains.

In this paper, we present an approach to evaluate the moral bounds of an AI system based on the monitoring of its inputs and outputs. We place a ‘Glass-Box’ around the system by mapping moral values into explicit verifiable norms that constrain inputs and outputs, in such a way that if these remain within the box we can guarantee that the system adheres to the value. The focus on inputs and outputs allows for the verification and comparison of vastly different intelligent systems; from deep neural networks to agent-based systems.

The explicit transformation of abstract moral values into concrete norms brings great benefits interms of explainability; stakeholders know exactly how the system is interpreting and employing relevant abstract moral human values and calibrate their trust accordingly. Moreover, by operating at a higher level we can check the compliance of the system with different interpretations of the same value.

Place, publisher, year, edition, pages
2019.
Keywords [en]
artificial intelligence, ethics, verification, safety, transparency
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:umu:diva-159953OAI: oai:DiVA.org:umu-159953DiVA, id: diva2:1322782
Conference
28th International Joint Conference on Artificial Intelligence (IJCAI-19), Macao, China, August 10-16, 2019.
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)EU, Horizon 2020, 825619Available from: 2019-06-11 Created: 2019-06-11 Last updated: 2019-06-13

Open Access in DiVA

No full text in DiVA

Other links

ArXiv

Authority records BETA

Aler Tubella, AndreaTheodorou, AndreasDignum, FrankDignum, Virginia

Search in DiVA

By author/editor
Aler Tubella, AndreaTheodorou, AndreasDignum, FrankDignum, Virginia
By organisation
Umeå University
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 185 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf