# Fractal Signatures: Securing AI-Generated Pollock-Style Art via Intrinsic Watermarking and Blockchain

arXiv: https://arxiv.org/abs/2410.20519 · HTML: https://mlsanity.com/paper/2410.20519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 27 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [StyleBank: An Explicit Representation for Neural Image Style Transfer](https://mlsanity.com/paper/1703.09210/) (2017)
- [Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer](https://mlsanity.com/paper/1612.01895/) (2016)
- [Non-Fungible Token (NFT): Overview, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2105.07447/) (2021)
- [Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash](https://mlsanity.com/paper/2111.06628/) (2021)
- [Mapping the NFT revolution: market trends, trade networks and visual features](https://mlsanity.com/paper/2106.00647/) (2021)
- [A Review of zk-SNARKs](https://mlsanity.com/paper/2202.06877/) (2022)
- [Networks of Ethereum Non-Fungible Tokens: A graph-based analysis of the ERC-721 ecosystem](https://mlsanity.com/paper/2110.12545/) (2021)

## Abstract (arXiv)

The digital art market faces unprecedented challenges in authenticity verification and copyright protection. This study introduces an integrated framework to address these issues by combining neural style transfer, fractal analysis, and blockchain technology. We generate abstract artworks inspired by Jackson Pollock, using their inherent mathematical complexity to create robust, imperceptible watermarks. Our method embeds these watermarks, derived from fractal and turbulence features, directly into the artwork's structure. This approach is then secured by linking the watermark to NFT metadata, ensuring immutable proof of ownership. Rigorous testing shows our feature-based watermarking achieves a 76.2% average detection rate against common attacks, significantly outperforming traditional methods (27.8-44.0%). This work offers a practical solution for digital artists and collectors, enhancing security and trust in the digital art ecosystem.