# DIS-CO: Discovering Copyrighted Content in VLMs Training Data

arXiv: https://arxiv.org/abs/2502.17358 · HTML: https://mlsanity.com/paper/2502.17358/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 35 of its 44 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [Do Membership Inference Attacks Work on Large Language Models?](https://mlsanity.com/paper/2402.07841/) (2024)
- [Pixtral 12B](https://mlsanity.com/paper/2410.07073/) (2024)
- [Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks](https://mlsanity.com/paper/2203.03929/) (2022)
- [On the Importance of Difficulty Calibration in Membership Inference Attacks](https://mlsanity.com/paper/2111.08440/) (2021)
- [LLM Dataset Inference: Did you train on my dataset?](https://mlsanity.com/paper/2406.06443/) (2024)
- [Copyright Violations and Large Language Models](https://mlsanity.com/paper/2310.13771/) (2023)
- [Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models](https://mlsanity.com/paper/2404.02936/) (2024)
- [Understanding Membership Inferences on Well-Generalized Learning Models](https://mlsanity.com/paper/1802.04889/) (2018)
- [DE-COP: Detecting Copyrighted Content in Language Models Training Data](https://mlsanity.com/paper/2402.09910/) (2024)
- [Blind Baselines Beat Membership Inference Attacks for Foundation Models](https://mlsanity.com/paper/2406.16201/) (2024)
- [Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models](https://mlsanity.com/paper/2310.15007/) (2023)
- [Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method](https://mlsanity.com/paper/2409.14781/) (2024)
- [Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs](https://mlsanity.com/paper/2406.10209/) (2024)
- [Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data](https://mlsanity.com/paper/2409.19798/) (2024)

## Built on by (most cited first, 1 of 1)

- [RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline](https://mlsanity.com/paper/2510.25941/) (2025)

## Abstract (arXiv)

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. Our code and data are available at https://github.com/avduarte333/DIS-CO