Deep Learning Framework for Intellectual Property Authentication of Digital Artworks
Journal of Al-Farabi for Engineering Sciences · 11.06.2026 · 5 (1) · 122-143
DOI: 10.59746/ksgkaq11 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Al-Farabi for Engineering Sciences, online erschienen am 11.06.2026. Verfasst von Jasim Mohammed Atiyah.
Abstract (Originalsprache)
The fast growth of production and dissemination of digital art via websites and artificial intelligence technology has posed serious issues in the field of protecting intellectual property and authentication verification. Current methods sometimes have difficulty telling actual artworks apart from real derivative works and copyright-infringing material, especially with complex digital adjustments or AI-generated changes. This research work aims to propose an intelligent framework for the verification and copyright protection of digital artwork. The proposed framework combines deep feature extraction, semantics graph construction, a Graph-Manifold invariant representational learning and classification based on machine learning to accurately classify original, derivative and infringing artworks. The proposed framework includes of several sequential stages such as image preprocessing and normalization, salient region detection, a deep the extraction of features, semantic graph structure, Graph-Manifold based invariant feature learning, feature similarity measurement performed by cosine similarity and final classification by Support Vector Machine (SVM). The benchmark dataset consisted of 9,000 digital artworks comprising original artworks, lawful derivatives and copyright infringing pictures acquired via sophisticated modification and AI based approaches. The experimental results showed that the suggested framework performed better than the current techniques. The semantic Graph-Manifold framework achieved a general accuracy in classification of 98.1%, F1 score of 0.967 and AUC value of 0.982. Unaffected by image edits, stylistic shifts, or AI-generated adjustments, the system could distinguish between legitimate derivative works and those that infringed on copyrights. Semantic graphing, graph-based representational learning, and support vector machine classification all work together to provide a solid strategy for ensuring the legitimacy of digital artworks and safeguarding intellectual property. In modern AI-driven creative environments, the proposed approach offers a practical answer to the problems of copyright management and through the internet asset protection while simultaneously improving semantic understanding, classification accuracy, and misclassification rates.
Zitieren
APA
Atiyah, J. M. (2026). Deep Learning Framework for Intellectual Property Authentication of Digital Artworks. Journal of Al-Farabi for Engineering Sciences, 5(1), 122-143. https://doi.org/10.59746/ksgkaq11
Vancouver
Atiyah JM. Deep Learning Framework for Intellectual Property Authentication of Digital Artworks. Journal of Al-Farabi for Engineering Sciences. 2026;5(1):122-143. doi:10.59746/ksgkaq11
BibTeX
@article{Atiyah2026,
author = {Atiyah, Jasim Mohammed},
title = {Deep Learning Framework for Intellectual Property Authentication of Digital Artworks},
journal = {Journal of Al-Farabi for Engineering Sciences},
year = {2026},
volume = {5},
number = {1},
pages = {122--143},
doi = {10.59746/ksgkaq11}
}
EUVIMED