ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models
Text-to-image models based on diffusion processes, such as DALL-E, Stable Diffusion, and Midjourney, are capable of transforming texts into detailed images and have widespread applications in art and design. As such, amateur users can easily imitate professional-level paintings by collecting an artist's work and fine-tuning the model, leading to concerns about artworks' copyright infringement. To tackle these issues, previous studies either add visually imperceptible perturbation to the artwork to change its underlying styles (perturbation-based methods) or embed post-training detectable watermarks in the artwork (watermark-based methods). However, when the artwork or the model has been published online, i.e., modification to the original artwork or model retraining is not feasible, these strategies might not be viable.
Authors
- Peng Cheng (ORCID: https://orcid.org/0000-0002-4221-2162)
- Shouling Ji (ORCID: https://orcid.org/0000-0003-4268-372X)
- Linkang Du (ORCID: https://orcid.org/0009-0004-9028-9326)
- Min Chen (ORCID: https://orcid.org/0000-0002-1128-7989)
- Jiming Chen (ORCID: https://orcid.org/0000-0003-3155-3145)
- Zhikun Zhang (ORCID: https://orcid.org/0000-0001-7208-3392)
- Zhou Su (ORCID: https://orcid.org/0000-0002-2875-0458)
- Zheng Zhu
Institutions
- Chinese University of Hong Kong (HK)
- Hangzhou Dianzi University (CN)
- Zhejiang University (CN)
- Vrije Universiteit Amsterdam (NL)
- Xi'an Jiaotong University (CN)
Publication Details
- Published
- 2025-04-22
- DOI
- https://doi.org/10.1145/3696410.3714602
- Citations
- 1
- Primary Topic
- Generative Adversarial Networks and Image Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 1.28
Funders
- National Natural Science Foundation of China
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek
- Zhejiang University
- National Key Research and Development Program of China