liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Formal Verification of Input-Output Mappings of Tree Ensembles
Linköping University, Department of Computer and Information Science, Software and Systems. Linköping University, Faculty of Science & Engineering. (Real-Time Systems Laboratory)
Linköping University, Department of Computer and Information Science, Software and Systems. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-1485-0802
2020 (English)In: Science of Computer Programming, ISSN 0167-6423, E-ISSN 1872-7964, Vol. 194Article in journal (Refereed) Published
Abstract [en]

Recent advances in machine learning and artificial intelligence are now beingconsidered in safety-critical autonomous systems where software defects maycause severe harm to humans and the environment. Design organizations in thesedomains are currently unable to provide convincing arguments that their systemsare safe to operate when machine learning algorithms are used to implement theirsoftware.

In this paper, we present an efficient method to extract equivalence classes from decision trees and tree ensembles, and to formally verify that their input-output mappings comply with requirements. The idea is that, given that safety requirements can be traced to desirable properties on system input-output patterns, we can use positive verification outcomes in safety arguments.

This paper presents the implementation of the method in the tool VoTE (Verifier of Tree Ensembles), and evaluates its scalability on two case studies presented in current literature. We demonstrate that our method is practical for tree ensembles trained on low-dimensional data with up to 25 decision trees and tree depths of up to 20.Our work also studies the limitations of the method with high-dimensionaldata and preliminarily investigates the trade-off between large number of trees and time taken for verification.

Place, publisher, year, edition, pages
2020. Vol. 194
Keywords [en]
Formal verification, Decision tree, Tree ensemble, Random forest, Gradient boosting machine
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:liu:diva-164563DOI: 10.1016/j.scico.2020.102450OAI: oai:DiVA.org:liu-164563DiVA, id: diva2:1416647
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)Available from: 2020-03-24 Created: 2020-03-24 Last updated: 2020-04-24

Open Access in DiVA

The full text will be freely available from 2022-03-19 12:13
Available from 2022-03-19 12:13

Other links

Publisher's full text

Authority records BETA

Törnblom, JohnNadjm-Tehrani, Simin

Search in DiVA

By author/editor
Törnblom, JohnNadjm-Tehrani, Simin
By organisation
Software and SystemsFaculty of Science & Engineering
In the same journal
Science of Computer Programming
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 20 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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