Fantastic Copyrighted Beasts and How (Not) to Generate Them

ICLR 2025 Conference Submission7139 Authors

Keywords: copyright, copyrighted characters, alignment, evaluation, image generation models

Abstract:

Recent studies show that image and video generation models can be prompted to reproduce copyrighted content from their training data, raising serious legal concerns about copyright infringement. Copyrighted characters (e.g., Mario, Batman) present a significant challenge: at least one lawsuit has already awarded damages based on the generation of such characters. Consequently, commercial services like DALL·E have started deploying interventions.
However, little research has systematically examined these problems: (1) Can users easily prompt models to generate copyrighted characters, even if it is unintentional?; (2) How effective are the existing mitigation strategies?
To address these questions, we introduce a novel evaluation framework with metrics that assess both the generated image’s similarity to copyrighted characters and its consistency with user intent, grounded in a set of popular copyrighted characters from diverse studios and regions.
We show that state-of-the-art image and video generation models can still generate characters even if characters' names are not explicitly mentioned, sometimes with only two generic keywords (e.g., prompting with ``videogame, plumber'' consistently generates Nintendo's Mario character).
We also introduce semi-automatic techniques to identify such keywords or descriptions that trigger character generation. Within this framework, we study the effectiveness of mitigation strategies, including both existing methods and new strategies we propose. Our findings reveal that commonly used strategies, such as prompt rewriting in DALL·E, are insufficient as standalone guardrails. These strategies need to be supplemented with other approaches, such as negative prompting, to effectively reduce the unintended generation of copyrighted characters. Our work provides empirical grounding for discussions on copyright mitigation strategies and offers actionable insights for model deployers implementing these safeguards.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 7139