EUVIMEDEUVIMED entdecken
Crossref

Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy

Xiafeng Man, Zhipeng Wei, Jingjing Chen

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (10) · 7910-7917

DOI: 10.1609/aaai.v40i10.37735 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xiafeng Man und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread deployment of large vision models such as Stable Diffusion raises significant legal and ethical concerns, as these models can memorize and reproduce copyrighted content without authorization. Existing detection approaches often lack robustness and fail to provide rigorous theoretical underpinnings. To address these gaps, we formalize the concept of copyright infringement and its detection from the perspective of Differential Privacy (DP), and introduce the conditional sensitivity metric, a concept analogous to sensitivity in DP, that quantifies the deviation in a diffusion model's output caused by the inclusion or exclusion of a specific training data point. To operationalize this metric, we propose D-Plus-Minus (DPM), a novel post-hoc detection framework that identifies copyright infringement in text-to-image diffusion models. Specifically, DPM simulates inclusion and exclusion processes by fine-tuning models in two opposing directions: learning or unlearning. Besides, to disentangle concept-specific influence from the global parameter shifts induced by fine-tuning, DPM computes confidence scores over orthogonal prompt distributions using statistical metrics. Moreover, to facilitate standardized benchmarking, we also construct the Copyright Infringement Detection Dataset (CIDD), a comprehensive resource for evaluating detection across diverse categories. Our results demonstrate that DPM reliably detects infringement content without requiring access to the original training dataset or text prompts, offering an interpretable and practical solution for safeguarding intellectual property in the era of generative AI.

Zitieren

APA

Man, X., Wei, Z., & Chen, J. (2026). Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy. Proceedings of the AAAI Conference on Artificial Intelligence, 40(10), 7910-7917. https://doi.org/10.1609/aaai.v40i10.37735

Vancouver

Man X, Wei Z, Chen J. Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(10):7910-7917. doi:10.1609/aaai.v40i10.37735

BibTeX
@article{Man2026,
  author = {Man, Xiafeng and Wei, Zhipeng and Chen, Jingjing},
  title = {Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {10},
  pages = {7910--7917},
  doi = {10.1609/aaai.v40i10.37735}
}
Kostenlos starten →