Industry 4.0
Vol. 11 (2026), Issue 1, pg(s) 38-41

SOCIETY & ”INDUSTRY 4.0”

AI-based technologies in the authentication of fine art: toward a hybrid epistemology of cultural trust

  • 1 Sofia, Bulgaria

Abstract

The authentication of fine art has customarily relied on expert connoisseurship, material analysis, and provenance research. In recent years, artificial intelligence (AI) and AI-based technologies have appeared as significant tools in this domain, enabling new forms of algorithmic evidence, probabilistic reasoning, and large-scale pattern recognition. This paper examines how AI-based systems support museums, galleries, collectors, and private institutions in authenticating fine art paintings. It argues that AI does not replace human expertise but establishes a hybrid epistemic framework in which algorithmic forensics and art-historical knowledge co-produce authenticity. The study analyses key technological approaches, institutional applications, epistemological implications, and structural drawbacks, positioning AI as a catalytic agent in reconfiguring trust, authority, and knowledge production within the contemporary art ecosystem.

Keywords

References

  1. A Adorni, G. & Bellini, E. (2025). Towards a Manifesto for Cyber Humanities: Paradigms, Ethics, and Prospects. arXiv preprint. https://doi.org/10.48550/arXiv.2508.02760, Accessed: 10.02.2026
  2. Lawson-Tancred, J., (2025). AI and the Art Market (Hot Topics in the Art World). https://oceanofpdf.com/authors/jo-lawson-tancred/pdf-epub-ai-and-the-art-market-hot-topics-in-the-art-world-download/, Accessed: 12.02.2026
  3. Polak, A., Kelman, T., Murray, P., Marshall, S., (2017). Hyperspectral imaging combined with data classification techniques as an aid for artwork authentication. https://www.researchgate.net/publication/314670114_Hyperspectral _imaging_combined_with_data_classification_techniques_as_an_ai d_for_artwork_authentication, Accessed: 15.02.2026
  4. Dobbs, T., Nayeem, A., Cho, I. & Ras, Z. (2023). Contemporary Art Authentication with Large-Scale Classification. Big Data Cogn. Comput. https://doi.org/10.3390/bdcc7040162, Accessed 01.02.2026
  5. Elgammal, A., Mazzone, M., Liu, B., Kim, D., & Elhoseiny, M. (2018). The Shape of Art History in the Eyes of the Machine. https://www.researchgate.net/publication/322694894, Accessed: 01.02.2026
  6. Expert Systems with Applications. (2022). On art authentication and the Rijksmuseum challenge: A residual neural network approach, 202. https://doi.org/10.1016/j.eswa.2022.116933, Accessed: 05.02.2026
  7. Getty Research Institute. (May 1, 2025). Getty Transforms Art Provenance Data to Support 21st Century Research. Getty News. https://www.getty.edu/news/getty-transforms-art-provenance-data-to-support-21st-century-research/, Accessed: 07.02.2026
  8. Johnson, C. R., Hendriks, E., Berezhnoy, I., et al. (2008). Image processing for artist identification. https://ericpostma.nl/publications/Johnsonetal2008.pdf, Accessed: 11.02.2026
  9. Münster, S., et al. (2019). Digital cultural heritage meets digital humanities. https://www.researchgate.net/publication/335417192_DIGITAL_C ULTURAL_HERITAGE_MEETS_DIGITAL_HUMANITIES, Accessed: 07.02.2026
  10. Silva, R. S., Lotfi, A., Ihianle, I. K., Shahtahmassebi, G., & Bird, J. J. (2024). ArtBrain: An Explainable End-to-End Toolkit for Classification and Attribution of AI-Generated Art and Style. arXiv preprint. https://doi.org/10.48550/arXiv.2412.01512, Accessed: 10.02.2026
  11. Thiel, S. & Bernhardt, J. C. (2024). AI in Museums: Reflections, Perspectives and Applications. transcript publishing. https://library.oapen.org/bitstream/handle/20.500.12657/87430/1/97 83839467107.pdf?trk=public_post_comment-text, Accessed: 02.02.2026
  12. Tom's Hardware. (June 14, 2025). ASML's Impasto Project creates 3D digital twins of Vincent van Gogh's art with 100 gigabytes of data per scan. https://www.tomshardware.com/3d-printing/3d-scanning/asmls-impasto-project-creates-3d-digital-twins-of-vincent-van-goghs-art-with-100-gigabytes-of-data-per-scan-nanometer-capable-chipmaking-tech-used-to-create-google-maps-for-paintings
  13. Wang, Z. & Song, H. (2025). A Fusion Model for Artwork Identification Based on Convolutional Neural Networks and Transformers.. https://doi.org/10.48550/arXiv.2502.18083, Accessed: 08.02.2026
  14. Centre for Art Law. (2025). Framework for Responsible Use of AI in Art Authentication. https://itsartlaw.org/ai-and-art-authentication-guidelines/, Accessed: 04.02.2026

Article full text

Download PDF