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
Linking Architectural Threat Modeling of AI Systems to MITRE ATLAS via Semantic Knowledge Graphs
RISE Research Institutes of Sweden, Digital Systems, Mobility and Systems.ORCID iD: 0000-0002-8511-6867
RISE Research Institutes of Sweden, Digital Systems, Mobility and Systems.ORCID iD: 0000-0002-3906-7611
RISE Research Institutes of Sweden, Digital Systems, Mobility and Systems.ORCID iD: 0000-0002-1139-4266
2026 (English)In: Lecture Notes in Computer Science, Springer Nature , 2026, Vol. 16390 LNCS, p. 24-40Conference paper, Published paper (Refereed)
Abstract [en]

This paper demonstrates how semantic knowledge graph integration can bridge organizational threat modeling and adversarial frameworks for responsible AI security assessment. We applied ThreatFinder.ai to an AI-based facial anonymization system, identifying 12 assets, 33 instantiated threats (7 unique), and 157 instantiated controls (28 unique). These outputs were transformed into knowledge graphs and semantically linked to MITRE ATLAS using Sentence-BERT embeddings, creating explicit, auditable mappings between organizational threats and adversarial techniques. The linking produced 123 threat→technique, 72 threat→SubTechnique, and 21 control→mitigation alignments (covering 55 unique threats and 15 unique controls), enabling asset-centric reasoning and transparent security decision-making. The methodology satisfies multiple stakeholder needs: organizational usability through familiar workflows, governance compliance through auditable relations, and ethical transparency through accessible visualizations. These results show that interdisciplinary requirements can drive approaches to AI security that are both technically rigorous and practically usable

Place, publisher, year, edition, pages
Springer Nature , 2026. Vol. 16390 LNCS, p. 24-40
Keywords [en]
Adversarial ML, AI security, Responsible AI, Semantic knowledge graphs, Threat modeling
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:ri:diva-81159DOI: 10.1007/978-3-032-16886-3_2Scopus ID: 2-s2.0-105031292344ISBN: 9783032168856 (print)OAI: oai:DiVA.org:ri-81159DiVA, id: diva2:2046576
Conference
1st Interdisciplinary Workshop on Responsible AI for Value Creation, REPAI-W 2025
Note

This research was funded by the Swedish innovation agency Vinnova under the project Anonymization Defense GUARD (GUarding Anonymization pRoceDures) (reference number: 2023-02996). This work was also supported in part by the European Union\u2019s Horizon Europe research and innovation programme through the project ATHENA \u2013 An exposition on THe forEign informatioN mAnipulation and interference (Grant Agreement 101132686 ATHENA HORIZON-CL2-2023-DEMOCRACY-01). The authors are also grateful to Martin Torstensson for setting up the GUARD project and to Dr. Felix Rosberg for providing access to the facial anonymization models.

QC 20260318

Available from: 2026-03-17 Created: 2026-03-17 Last updated: 2026-05-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Rosell, JoakimUlan, MariaFransson, Max

Search in DiVA

By author/editor
Rosell, JoakimUlan, MariaFransson, Max
By organisation
Mobility and Systems
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 165 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