How to Evaluate and Mitigate IP Infringement in Visual Generative AI?

Zhenting Wang, Chen Chen, Vikash Sehwag, Minzhou Pan, Lingjuan Lyu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62555-62574, 2025.

Abstract

The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking resemblance to characters protected by intellectual property rights held by major entertainment companies (such as Sony, Marvel, and Nintendo), which raises potential legal concerns. This happens when the input prompt contains the character’s name or even just descriptive details about their characteristics. To mitigate such IP infringement problems, we also propose a defense method against it. In detail, we develop a revised generation paradigm that can identify potentially infringing generated content and prevent IP infringement by utilizing guidance techniques during the diffusion process. It has the capability to recognize generated content that may be infringing on intellectual property rights, and mitigate such infringement by employing guidance methods throughout the diffusion process without retrain or fine-tune the pretrained models. Experiments on well-known character IPs like Spider-Man, Iron Man, and Superman demonstrate the effectiveness of the proposed defense method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25o, title = {How to Evaluate and Mitigate {IP} Infringement in Visual Generative {AI}?}, author = {Wang, Zhenting and Chen, Chen and Sehwag, Vikash and Pan, Minzhou and Lyu, Lingjuan}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {62555--62574}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wang25o/wang25o.pdf}, url = {https://proceedings.mlr.press/v267/wang25o.html}, abstract = {The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking resemblance to characters protected by intellectual property rights held by major entertainment companies (such as Sony, Marvel, and Nintendo), which raises potential legal concerns. This happens when the input prompt contains the character’s name or even just descriptive details about their characteristics. To mitigate such IP infringement problems, we also propose a defense method against it. In detail, we develop a revised generation paradigm that can identify potentially infringing generated content and prevent IP infringement by utilizing guidance techniques during the diffusion process. It has the capability to recognize generated content that may be infringing on intellectual property rights, and mitigate such infringement by employing guidance methods throughout the diffusion process without retrain or fine-tune the pretrained models. Experiments on well-known character IPs like Spider-Man, Iron Man, and Superman demonstrate the effectiveness of the proposed defense method.} }
Endnote
%0 Conference Paper %T How to Evaluate and Mitigate IP Infringement in Visual Generative AI? %A Zhenting Wang %A Chen Chen %A Vikash Sehwag %A Minzhou Pan %A Lingjuan Lyu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wang25o %I PMLR %P 62555--62574 %U https://proceedings.mlr.press/v267/wang25o.html %V 267 %X The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking resemblance to characters protected by intellectual property rights held by major entertainment companies (such as Sony, Marvel, and Nintendo), which raises potential legal concerns. This happens when the input prompt contains the character’s name or even just descriptive details about their characteristics. To mitigate such IP infringement problems, we also propose a defense method against it. In detail, we develop a revised generation paradigm that can identify potentially infringing generated content and prevent IP infringement by utilizing guidance techniques during the diffusion process. It has the capability to recognize generated content that may be infringing on intellectual property rights, and mitigate such infringement by employing guidance methods throughout the diffusion process without retrain or fine-tune the pretrained models. Experiments on well-known character IPs like Spider-Man, Iron Man, and Superman demonstrate the effectiveness of the proposed defense method.
APA
Wang, Z., Chen, C., Sehwag, V., Pan, M. & Lyu, L.. (2025). How to Evaluate and Mitigate IP Infringement in Visual Generative AI?. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:62555-62574 Available from https://proceedings.mlr.press/v267/wang25o.html.

Related Material