View in EDS PDF Full Text

Concolic Testing on Individual Fairness of Neural Network Models.

Saved in:
Bibliographic Details
Title: Concolic Testing on Individual Fairness of Neural Network Models.
Authors: HUANG, MING-I.1 111356047@nccu.edu.tw, HONG, CHIH-DUO1 chihduo@nccu.edu.tw, YU, FANG1 yuf@nccu.edu.tw
Source: Journal of Information Science & Engineering. May2026, Vol. 42 Issue 3, p665-680. 16p.
Subjects: Fairness, Formal verification, Deep learning, Discrimination (Sociology), Computer software testing, Algorithmic bias, Artificial neural networks
Abstract: This paper introduces PyFair, a formal framework for evaluating and verifying individual fairness of Deep Neural Networks (DNNs). By adapting the concolic testing tool PyCT, we generate fairness-specific path constraints to systematically explore DNN behaviors. Our key innovation is a dual network architecture that enables comprehensive fairness assessments and provides completeness guarantees for certain network types. We evaluate PyFair on 25 benchmark models, including those enhanced by existing bias mitigation techniques. Results demonstrate PyFair's efficacy in detecting discriminatory instances and verifying fairness, while also revealing scalability challenges for complex models. This work advances algorithmic fairness in critical domains by offering a rigorous, systematic method for fairness testing and verification of pre-trained DNNs. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Information Science & Engineering is the property of Institute of Information Science, Academia Sinica and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 193961063
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Concolic Testing on Individual Fairness of Neural Network Models.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22HUANG%2C+MING-I%2E%22">HUANG, MING-I.</searchLink><relatesTo>1</relatesTo><i> 111356047@nccu.edu.tw</i><br /><searchLink fieldCode="AR" term="%22HONG%2C+CHIH-DUO%22">HONG, CHIH-DUO</searchLink><relatesTo>1</relatesTo><i> chihduo@nccu.edu.tw</i><br /><searchLink fieldCode="AR" term="%22YU%2C+FANG%22">YU, FANG</searchLink><relatesTo>1</relatesTo><i> yuf@nccu.edu.tw</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Information+Science+%26+Engineering%22">Journal of Information Science & Engineering</searchLink>. May2026, Vol. 42 Issue 3, p665-680. 16p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Fairness%22">Fairness</searchLink><br /><searchLink fieldCode="DE" term="%22Formal+verification%22">Formal verification</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Discrimination+%28Sociology%29%22">Discrimination (Sociology)</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+software+testing%22">Computer software testing</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithmic+bias%22">Algorithmic bias</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper introduces PyFair, a formal framework for evaluating and verifying individual fairness of Deep Neural Networks (DNNs). By adapting the concolic testing tool PyCT, we generate fairness-specific path constraints to systematically explore DNN behaviors. Our key innovation is a dual network architecture that enables comprehensive fairness assessments and provides completeness guarantees for certain network types. We evaluate PyFair on 25 benchmark models, including those enhanced by existing bias mitigation techniques. Results demonstrate PyFair's efficacy in detecting discriminatory instances and verifying fairness, while also revealing scalability challenges for complex models. This work advances algorithmic fairness in critical domains by offering a rigorous, systematic method for fairness testing and verification of pre-trained DNNs. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Information Science & Engineering is the property of Institute of Information Science, Academia Sinica and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193961063
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.6688/JISE.202605_42(3).0011
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 665
    Subjects:
      – SubjectFull: Fairness
        Type: general
      – SubjectFull: Formal verification
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Discrimination (Sociology)
        Type: general
      – SubjectFull: Computer software testing
        Type: general
      – SubjectFull: Algorithmic bias
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
    Titles:
      – TitleFull: Concolic Testing on Individual Fairness of Neural Network Models.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: HUANG, MING-I.
      – PersonEntity:
          Name:
            NameFull: HONG, CHIH-DUO
      – PersonEntity:
          Name:
            NameFull: YU, FANG
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 10162364
          Numbering:
            – Type: volume
              Value: 42
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Journal of Information Science & Engineering
              Type: main
ResultId 1