Quantifying Likeness: A Simple Machine Learning Approach to Identifying Copyright Infringement in (AI-Generated) Artwork

Michaela Drouillard, Ryan Spencer, Nikée Nantambu-Allen, Tegan Maharaj

Keywords: generative ai, art, law, classification, copyright, resnet

TL;DR: We propose a simple, interpretable machine learning approach to quantify stylistic similarity between copyrighted and potentially infringing AI-generated artworks, aligning with legal processes for assessing substantial similarity in copyright cases.

Abstract:

This study proposes an approach aligned with the legal process to quantify copyright infringement, via stylistic similarity, in AI-generated artwork. In contrast to typical work in this field, and more in line with a realistic legal setting, our approach quantifies the similarity of a set of potentially-infringing “defendant” artworks to a set of copyrighted “plaintiff" artworks. We frame this as an image classification task, using a fine-tuned ResNet trained on small, customized datasets relevant to each use case. Softmax-normalized probabilities from the model serve as similarity scores for potentially infringing “defendant” artworks, and saliency maps and features visualizations complement the score by highlighting key features and allowing for interpretability. This straightforward image classification approach can be accomplished in a quite simple, low-resource setting, making it accessible for real-world applications.

We present a case study using Mickey Mouse as the plaintiff, performing thorough hyperparameter tuning and robustness analysis. Our experiments include optimizing batch size, weight decay, and learning rate, as well as exploring the impact of additional distractor classes. We employ data augmentation, cross-validation, and a linear decay learning rate scheduler to improve model performance, along with conducting scaling experiments with different types of distractor classes. The aims of this work are to illustrate the potential of the approach, and identify settings which generalize well, such that it is as "plug and play" as possible for users to apply with their own plaintiff sets of artworks.

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: 12013