Deep Learning Framework for Intellectual Property Authentication of Digital Artworks
DOI:
https://doi.org/10.59746/ksgkaq11Keywords:
Deep Learning, Visual Similarity Detection, Graph-Manifold Learning, Digital Copyright Protection, Support Vector Machine, Artificial Intelligence Generated ArtAbstract
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.
References
[1] Chen, B., & Chen, S. (2026). Deep learning. In B. Chen & S. Chen (Eds.), Machine Vision Technology (pp. 273–297). Springer Nature Singapore. https://doi.org/10.1007/978-981-95-1184-6_16
[2] Kaur, R., & Rani, S. (2023). Artificial intelligence and copyright protection challenges in digital art environments. Journal of Intellectual Property Rights, 28(2), 115–126. https://doi.org/10.56042/jipr.v28i2.7421
[3] Li, Y., Zhang, X., & Chen, H. (2022). Deep visual similarity learning for digital artwork authentication and copyright protection. Multimedia Tools and Applications, 81, 21435–21458. https://doi.org/10.1007/s11042-022-12475-8
[4] Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009). The graph neural network model. IEEE Transactions on Neural Networks, 20(1), 61–80. https://doi.org/10.1109/TNN.2008.2005605
[5] Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021). A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 4–24. https://doi.org/10.1109/TNNLS.2020.2978386
[6] Zhang, Y., Wang, J., & Luo, X. (2021). Deepfake image detection and digital media authenticity analysis using deep learning techniques. IEEE Access, 9, 68245–68258. https://doi.org/10.1109/ACCESS.2021.3077865.
[7] Harsanto, K., Zaidan, M. T., Lucky, H., & Suhartono, D. (2024). Detecting AI-generated artworks with deep learning. In 2024 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) (pp. 472–476). IEEE. https://doi.org/10.1109/ICIMCIS64264.2024.10870752
[8] Sajid, M., et al. (2025). Comparative analysis of text-based plagiarism detection techniques. PLOS ONE, 20(4), e0319551. https://doi.org/10.1371/journal.pone.0319551
[9] Hur, H., et al. (2024). Latent diffusion models for image watermarking: A review of recent trends and future directions. Electronics, 14(1), 25. https://doi.org/10.3390/electronics14010025
[10] Ghiurău, D., & Popescu, D. E. (2024). Distinguishing reality from AI: Approaches for detecting synthetic content. Computers, 14(1), 1. https://doi.org/10.3390/computers14010001
[11] Xu, J., Zhang, J., & Wang, J. (2025). Digital image copyright protection and management approach—Based on artificial intelligence and blockchain technology. Journal of Theoretical and Applied Electronic Commerce Research, 20(2), 76. https://doi.org/10.3390/jtaer20020076
[12] Jin, X., & Tan, J. (2025). Plagiarism detection of anime character portraits. Expert Systems with Applications, 261, 125566. https://doi.org/10.1016/j.eswa.2024.125566
[13] Khemani, B., et al. (2024). A review of graph neural networks: Concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data, 11(1), 18. https://doi.org/10.1186/s40537-024-00877-5
[14] Al Busaidi, H. H., Malik, A., & Tarhini, A. (2025, September). A Systematic Review of Generative AI in Self-Diagnosis: Benefits, Risks, and Ethical Challenges. In International Working Conference on Transfer and Diffusion of IT (pp. 194-213). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-16779-8_15
[15] Wang, T., et al. (2023). Ultra-high-definition low-light image enhancement: A benchmark and transformer-based method. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 2654–2662. https://doi.org/10.1609/aaai.v37i3.25464
[17] Shinde, P. P., & Shah, S. (2018). A review of machine learning and deep learning applications. In 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA) (pp. 1–6). IEEE. https://doi.org/10.1109/ICCUBEA.2018.8697857
[18] Shafiq, M., & Gu, Z. (2022). Deep residual learning for image recognition: A survey. Applied Sciences, 12(18), 8972. https://doi.org/10.3390/app12188972
[19] Li, M. M., Huang, K., & Zitnik, M. (2022). Graph representation learning in biomedicine and healthcare. Nature Biomedical Engineering, 6(12), 1353–1369. https://doi.org/10.1038/s41551-022-00942-x
[20] Luo, X., et al. (2023). Towards semi-supervised universal graph classification. IEEE Transactions on Knowledge and Data Engineering, 36(1), 416–428. https://doi.org/10.1109/TKDE.2022.3225488
[21] Jegelka, S. (2023). Theory of graph neural networks: Representation and learning. In Proceedings of the International Congress of Mathematicians 2022 (Vol. 7, pp. 5450–5476). EMS Press. https://doi.org/10.4171/ICM2022/162
[22] Ju, W., Mao, Z., Yi, S., Qin, Y., Gu, Y., Xiao, Z., Shen, J., Qiao, Z., & Zhang, M. (2025). Cluster-guided contrastive class-imbalanced graph classification. Proceedings of the AAAI Conference on Artificial Intelligence, 39(11), 11924–11932. https://doi.org/10.1609/aaai.v39i11.33298
[23] Bishop, C. M. (2006). Pattern recognition and machine learning. Springer. https://doi.org/10.1007/978-0-387-45528-0
[24] Jabardi, M. (2025). Support vector machines: Theory, algorithms, and applications. Infocommunications Journal, 17(1), 66–75. https://doi.org/10.4108/eetin.v17i1.8522
