Artify: An AI Powered Blockchain Based Art Authentication and Provenance Platform

Abstract

This paper presents an intelligent, AI-powered blockchain-based system designed to automate artwork authentication and provenance tracking in digital marketplaces, addressing the growing challenge of art forgery, duplication, and lack of transparent ownership verification, which are time-consuming, unreliable, and prone to manipulation in traditional systems. The proposed system integrates a multimodal data processing pipeline that analyses artwork images, textual descriptions, and metadata, enabling the generation of a unique digital fingerprint for each artwork while supporting accurate duplicate detection and authenticity validation. The collected multimodal data is processed through a comprehensive pipeline involving image embedding extraction using CLIP-based vision transformers, text embedding using sentence transformers, feature normalization, and cosine similarity computation for cross-modal comparison. The processed data is then utilized within a hybrid similarity detection framework that identifies potential duplicates and ensures reliable verification of artwork originality. The system further incorporates cryptographic hashing using SHA-256 to generate secure identifiers, which are anchored onto the Polygon blockchain via smart contracts, ensuring immutable proof-of-creation and decentralized ownership tracking. Additionally, the system integrates a conversational AI module to enable seamless and user-friendly artwork registration, along with a QR-based verification mechanism for real-time authentication. The complete system is deployed using a scalable backend architecture with FastAPI and vector similarity search supported by Pinecone, enabling efficient retrieval, real-time validation, and secure management of artwork data.

Introduction

The text explains that the rapid growth of digital art platforms has made it easier to create and trade artworks, but it has also introduced issues like forgery, duplication, and lack of reliable ownership tracking. Traditional authentication methods are slow, manual, and vulnerable to manipulation.

To address these challenges, the proposed system Artify combines Artificial Intelligence, Blockchain, and Multimodal learning into a single platform. AI techniques (such as image and text analysis) are used to detect duplicate or fake artworks, while blockchain ensures secure, transparent, and tamper-proof ownership records. Multimodal models integrate image, text, and metadata to create a unique digital identity (fingerprint) for each artwork.

Artify works by collecting and preprocessing artwork data, extracting features using models like CLIP and transformers, and detecting similarity through cosine similarity. If the artwork is unique, a secure hash (digital fingerprint) is generated and stored on the Polygon blockchain for provenance tracking. The system also uses a vector database for efficient similarity search.

Additionally, Artify includes a conversational AI interface to make the platform user-friendly and accessible, especially for non-technical users. A QR-based verification system allows real-time authentication of artworks.

Results show that the multimodal system performs better than individual models, achieving high accuracy in detecting duplicates and ensuring authenticity. Overall, Artify provides a secure, scalable, and transparent solution for protecting digital art and managing ownership in modern marketplaces.

Conclusion

In this paper, Artify presents a robust solution for artwork authentication and provenance tracking by integrating Multimodal Artificial Intelligence and Blockchain technology. The system effectively addresses challenges such as forgery, duplication, and lack of transparent ownership by combining image and text-based analysis with secure digital fingerprinting. The use of CLIP and Sentence Transformers enables accurate duplicate detection, while cosine similarity ensures reliable comparison across multimodal data. The implementation of SHA-256 hashing and Polygon blockchain provides a decentralized and tamper-proof mechanism for storing artwork records, ensuring data integrity and trust. Additionally, the inclusion of Conversational AI simplifies the artwork registration process, making the platform accessible to non-technical users. The QR-based verification system further enhances usability by enabling real-time authentication of artworks. Overall, the proposed system demonstrates high accuracy, scalability, and security, making it a practical solution for modern digital art ecosystems. By bridging the gap between intelligent verification and decentralized storage, Artify contributes towards building a transparent, reliable, and user-friendly platform for protecting intellectual property and promoting trust in digital art marketplaces.

References

[1] X. Chen et al., “Towards Reliable Utilization of AIGC: Blockchain-Empowered Ownership Verification Mechanism,” IEEE Open Journal of the Computer Society, vol. 4, pp. 326–337, 2023. [2] Y. Hassanzadeh-Nazarabadi, A. Küpçü, and O. Özkasap, “LightChain: Scalable DHT-Based Blockchain,” IEEE Transactions on Parallel and Distributed Systems, vol. 32, no. 10, pp. 2582–2593, 2021. [3] L. Sun, X. Bai, C. Zhang, and W. Guo, “BSTProv: Blockchain-Based Secure and Trustworthy Data Provenance Sharing,” 2022. [4] M. Krichen, M. Ammi, and A. Mihoub, “Blockchain for Modern Applications: A Survey,” Sensors, vol. 22, no. 16, 2022. [5] R. Shinde et al., “Securing AI-Based Healthcare Systems Using Blockchain Technology,” 2022. [6] W. Zhang et al., “ScrollTimes: Tracing the Provenance of Paintings,” IEEE Transactions on Visualization and Computer Graphics, vol. 30, no. 6, pp. 2981–2994, 2024. [7] J. Sharma, A. Carvalho, and S. Bhunia, “Provenance of AI-Generated Images: A Vector Similarity and Blockchain-Based Approach,” 2025. [8] A. Mohit, B. Aggarwal, and C. Gondhalekar, “Provenance Verification of AI-Generated Images via Blockchain,” 2026. [9] M. Manik, M. Islam, and G. Wang, “SlideChain: Semantic Provenance via Blockchain,” 2025. [10] S. Bhushan et al., “Untangling Blockchain Technology: A Survey,” Computers & Electrical Engineering, vol. 90, 2021. [11] M. Mamdouh et al., “Authentication and Identity Management of IoT Devices,” Computers & Security, 2021. [12] S. Namasudra et al., “Blockchain: State-of-the-Art and Research Challenges,” Archives of Computational Methods in Engineering, 2021. [13] M. Mashatan et al., “Consumer Trust in Blockchain-Based Payments,” IEEE Access, 2022. [14] S. Aggarwal, N. Kumar, and S. Tanwar, “Blockchain-Envisioned UAV Communication,” IEEE Internet of Things Journal, vol. 8, no. 7, pp. 5416–5430, 2021. [15] R. Alkadi et al., “Blockchain Interoperability in UAV Networks,” IEEE Access, vol. 10, pp. 14463–14479, 2022. [16] B. Baliker et al., “Applications of Blockchain in FinTech,” IEEE Transactions on Engineering Management, 2024. [17] C. Chen et al., “Blockchain-Based Copyright Protection Scheme,” IEEE Transactions on Services Computing, vol. 16, no. 4, pp. 2316–2329, 2023. [18] F. Fernandez et al., “Stable Signature: Watermarking in Diffusion Models,” IEEE/CVF ICCV, 2023. [19] B. Zolfaghari and T. Koshiba, “Neural Networks and Cryptography,” Applied System Innovation, 2022. [20] Y. Wang et al., “Post-Quantum Cryptography in Blockchain Systems,” IEEE Access, vol. 13, pp. 112962–112977, 2025

Copyright

Copyright © 2026 Mr. Shanthosh, Sameer Sharma, Satyam Kumar, Akhil Reddy, Shambhu Yadav. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.