umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
The Glass Box Approach: Verifying Contextual Adherence to Values
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.ORCID-id: 0000-0002-8423-8029
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.ORCID-id: 0000-0001-7409-5813
2019 (Engelska)Konferensbidrag, Muntlig presentation med publicerat abstract (Refereegranskat)
Abstract [en]

Artificial Intelligence (AI) applications are beingused to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to be deployed safely, then people need to understand how the system is interpreting and whether it is adhering to the relevant moral values. Even though transparency is often seen as the requirement in this case, realistically it might notalways be possible or desirable, whereas the needto 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 contextual 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(s) in a specific context. 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–whereas by making the context explicit we exposethe different perspectives and frameworks that are taken into account when subsuming moral values into specific norms and functionalities. We present a modal logic formalisation of the Glass Box approach which is domain-agnostic, implementable, and expandable.

Ort, förlag, år, upplaga, sidor
2019.
Nyckelord [en]
artificial intelligence, safety, verification, ethics
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
datalogi
Identifikatorer
URN: urn:nbn:se:umu:diva-160949OAI: oai:DiVA.org:umu-160949DiVA, id: diva2:1330967
Konferens
AISafety 2019, Macao, August 11-12, 2019
Forskningsfinansiär
Wallenberg AI, Autonomous Systems and Software Program (WASP)Tillgänglig från: 2019-06-26 Skapad: 2019-06-26 Senast uppdaterad: 2019-06-27

Open Access i DiVA

Fulltext saknas i DiVA

Personposter BETA

Aler Tubella, AndreaDignum, Virginia

Sök vidare i DiVA

Av författaren/redaktören
Aler Tubella, AndreaDignum, Virginia
Av organisationen
Institutionen för datavetenskap
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 406 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf