Academic Journal
View in EDS

Evaluating the use of a novel expert system for interpretation of media authentication results.

Bibliographic Details
Title: Evaluating the use of a novel expert system for interpretation of media authentication results.
Authors: Epstein B; Magnet Forensics, Atlanta, Georgia, USA., Lyons B; Magnet Forensics, Madison, Wisconsin, USA., Fischer D; Magnet Forensics, Madison, Wisconsin, USA., Zlogar A; Magnet Forensics, Madison, Wisconsin, USA.
Source: Journal of forensic sciences [J Forensic Sci] 2026 Sep; Vol. 71 (5), pp. 2364-2372. Date of Electronic Publication: 2026 Jun 11.
Publication Type: Journal Article; Evaluation Study
Language: English
Journal Info: Publisher: Blackwell Pub Country of Publication: United States NLM ID: 0375370 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1556-4029 (Electronic) Linking ISSN: 00221198 NLM ISO Abbreviation: J Forensic Sci Subsets: MEDLINE
Imprint Name(s): Publication: 2006- : Malden, MA : Blackwell Pub.
Original Publication: [Chicago, Ill.] : Callaghan and Co., 1956-
MeSH Terms: Forensic Sciences*/methods , Expert Systems* , Artificial Intelligence*, Humans ; Algorithms ; Digital Media ; Video Recording
Abstract: The evolution of artificial intelligence has enabled the creation of hyper-realistic synthetic images and videos, significantly complicating the authentication of media evidence. Many algorithmic approaches to media authentication have proven ineffective in digital forensics, particularly due to the difficulty of expressing results from black-box algorithms. Compounding this challenge, practitioners face long examination times and an ever-increasing volume of media evidence in modern investigations. To address these challenges, the authors developed an artificial intelligence expert system incorporating several logic-based authentication tests related to media file structure, attribute similarity analysis, and internal file attributes. These tests were organized into distinct authentication pathways to produce concise, natural language conclusions comparable to opinions rendered by human examiners. The automated nature of an expert system may allow for demonstrably accurate results at scale without extensive human resources. This preliminary study compared the accuracy of the artificial intelligence expert system's opinions with those of trained human examiners from diverse digital forensic backgrounds. Both the expert system and the examiners were provided the same dataset, consisting of original, transmitted, edited, and synthetic videos. Both groups received file structure data, attribute similarity analyses, proprietary structural data, and metadata values. Using a 14-question survey, responses were collected and evaluated for accuracy, and error rates were calculated. Across 20 respondents, the human mean score was 69% as compared to the expert system score of 91%. These results can be used to evaluate the appropriateness of deploying artificial intelligence expert systems for forensic examinations, alongside human interpretations.
(© 2026 American Academy of Forensic Sciences.)
References: Forensic Sci Int. 2003 Jul 8;134(2-3):196-206. (PMID: 12850417)
J Forensic Sci. 2026 Sep;71(5):2364-2372. (PMID: 42277998)
Contributed Indexing: Keywords: artificial intelligence; expert system; interpretation of results; media authentication
Entry Date(s): Date Created: 20260612 Date Completed: 20260902 Latest Revision: 20260904
Update Code: 20260904
PubMed Central ID: PMC13534913
DOI: 10.1111/1556-4029.70377
PMID: 42277998
Database: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=15564029&ISBN=&volume=71&issue=5&date=20260901&spage=2364&pages=2364-2372&title=Journal of forensic sciences&atitle=Evaluating%20the%20use%20of%20a%20novel%20expert%20system%20for%20interpretation%20of%20media%20authentication%20results.&aulast=Epstein%20B&id=DOI:10.1111/1556-4029.70377
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42277998
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Evaluating the use of a novel expert system for interpretation of media authentication results.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Epstein+B%22">Epstein B</searchLink>; Magnet Forensics, Atlanta, Georgia, USA.<br /><searchLink fieldCode="AU" term="%22Lyons+B%22">Lyons B</searchLink>; Magnet Forensics, Madison, Wisconsin, USA.<br /><searchLink fieldCode="AU" term="%22Fischer+D%22">Fischer D</searchLink>; Magnet Forensics, Madison, Wisconsin, USA.<br /><searchLink fieldCode="AU" term="%22Zlogar+A%22">Zlogar A</searchLink>; Magnet Forensics, Madison, Wisconsin, USA.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%220375370%22">Journal of forensic sciences</searchLink> [J Forensic Sci] 2026 Sep; Vol. 71 (5), pp. 2364-2372. <i>Date of Electronic Publication: </i>2026 Jun 11.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article; Evaluation Study
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Blackwell+Pub%22">Blackwell Pub </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>0375370 <i>Publication Model: </i>Print-Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1556-4029 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2200221198%22">00221198 </searchLink><i>NLM ISO Abbreviation: </i>J Forensic Sci <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: 2006- : Malden, MA : Blackwell Pub.<br /><i>Original Publication</i>: [Chicago, Ill.] : Callaghan and Co., 1956-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Forensic+Sciences%22">Forensic Sciences*</searchLink>/<searchLink fieldCode="MM" term="%22Forensic+Sciences+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Expert+Systems%22">Expert Systems*</searchLink> <br /><searchLink fieldCode="MM" term="%22Artificial+Intelligence%22">Artificial Intelligence*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Algorithms%22">Algorithms</searchLink> ; <searchLink fieldCode="MH" term="%22Digital+Media%22">Digital Media</searchLink> ; <searchLink fieldCode="MH" term="%22Video+Recording%22">Video Recording</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The evolution of artificial intelligence has enabled the creation of hyper-realistic synthetic images and videos, significantly complicating the authentication of media evidence. Many algorithmic approaches to media authentication have proven ineffective in digital forensics, particularly due to the difficulty of expressing results from black-box algorithms. Compounding this challenge, practitioners face long examination times and an ever-increasing volume of media evidence in modern investigations. To address these challenges, the authors developed an artificial intelligence expert system incorporating several logic-based authentication tests related to media file structure, attribute similarity analysis, and internal file attributes. These tests were organized into distinct authentication pathways to produce concise, natural language conclusions comparable to opinions rendered by human examiners. The automated nature of an expert system may allow for demonstrably accurate results at scale without extensive human resources. This preliminary study compared the accuracy of the artificial intelligence expert system's opinions with those of trained human examiners from diverse digital forensic backgrounds. Both the expert system and the examiners were provided the same dataset, consisting of original, transmitted, edited, and synthetic videos. Both groups received file structure data, attribute similarity analyses, proprietary structural data, and metadata values. Using a 14-question survey, responses were collected and evaluated for accuracy, and error rates were calculated. Across 20 respondents, the human mean score was 69% as compared to the expert system score of 91%. These results can be used to evaluate the appropriateness of deploying artificial intelligence expert systems for forensic examinations, alongside human interpretations.<br /> (© 2026 American Academy of Forensic Sciences.)
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Forensic Sci Int. 2003 Jul 8;134(2-3):196-206. (PMID: <searchLink fieldCode="PM" term="%2212850417%22">12850417)</searchLink><br />J Forensic Sci. 2026 Sep;71(5):2364-2372. (PMID: <searchLink fieldCode="PM" term="%2242277998%22">42277998)</searchLink>
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>artificial intelligence; expert system; interpretation of results; media authentication
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260612 <i>Date Completed: </i>20260902 <i>Latest Revision: </i>20260904
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260904
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13534913
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1111/1556-4029.70377
– Name: AN
  Label: PMID
  Group: ID
  Data: 42277998
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42277998
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/1556-4029.70377
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 2364
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Digital Media
        Type: general
      – SubjectFull: Video Recording
        Type: general
      – SubjectFull: Forensic Sciences methods
        Type: general
      – SubjectFull: Expert Systems
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
    Titles:
      – TitleFull: Evaluating the use of a novel expert system for interpretation of media authentication results.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Epstein B
      – PersonEntity:
          Name:
            NameFull: Lyons B
      – PersonEntity:
          Name:
            NameFull: Fischer D
      – PersonEntity:
          Name:
            NameFull: Zlogar A
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: 2026 Sep
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1556-4029
          Numbering:
            – Type: volume
              Value: 71
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Journal of forensic sciences
              Type: main
ResultId 1