DIS-CO: Discovering Copyrighted Content in VLMs Training Data
André V. Duarte, Xuandong Zhao, Arlindo L. Oliveira, Lei Li
Abstract
*How can we verify whether copyrighted content was used to train a large vision-language model (VLM) without direct access to its training data?* Motivated by the hypothesis that a VLM is able to recognize images from its training corpus, we propose DIS-CO, a novel approach to infer the inclusion of copyrighted content during the model's development. By repeatedly querying a VLM with specific frames from targeted copyrighted material, DIS-CO extracts the content's identity through free-form text completions. To assess its effectiveness, we introduce MovieTection, a benchmark comprising 14,000 frames paired with detailed captions, drawn from films released both before and after a model’s training cutoff. Our results show that DIS-CO significantly improves detection performance, nearly doubling the average AUC of the best prior method on models with logits available. Our findings also highlight a broader concern: all tested models appear to have been exposed to some extent to copyrighted content. We provide the code in the supplementary materials.
BibTeX
@inproceedings{
duarte2025disco,
title={{DIS}-{CO}: Discovering Copyrighted Content in {VLM}s Training Data},
author={Andr{\'e} V. Duarte and Xuandong Zhao and Arlindo L. Oliveira and Lei Li},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=q0P4rrDImq}
}