# Can Large Vision-Language Models Detect Images Copyright Infringement from GenAI?

arXiv: https://arxiv.org/abs/2502.16618 · HTML: https://mlsanity.com/paper/2502.16618/

## Key facts

- Cited by 8 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 17 of its 33 references that are in the map.
- First posted on arXiv 23 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, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022)
- [Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts](https://mlsanity.com/paper/2309.06135/) (2023)
- [What Makes Good Examples for Visual In-Context Learning?](https://mlsanity.com/paper/2301.13670/) (2023)
- [Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond](https://mlsanity.com/paper/2304.04968/) (2023)
- [Visual In-Context Prompting](https://mlsanity.com/paper/2311.13601/) (2023)
- [Evaluating and Mitigating IP Infringement in Visual Generative AI](https://mlsanity.com/paper/2406.04662/) (2024)

## Built on by (most cited first, 8 of 8)

- [CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems](https://mlsanity.com/paper/2505.19405/) (2025)
- [AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models](https://mlsanity.com/paper/2509.00641/) (2025)
- [Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy](https://mlsanity.com/paper/2509.23022/) (2025)
- [The Persistence of Cultural Memory: Investigating Multimodal Iconicity in Diffusion Models](https://mlsanity.com/paper/2511.11435/) (2025)
- [Overcoming the Curvature Bottleneck in MeanFlow](https://mlsanity.com/paper/2511.23342/) (2025)
- [Copyright Infringement Risk Reduction via Chain-of-Thought and Task Instruction Prompting](https://mlsanity.com/paper/2512.15442/) (2025)
- [Evaluating Intellectual Property Guardrails of Generative Image Models: A Technical Report](https://mlsanity.com/paper/2607.02582/) (2026)
- [DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection](https://mlsanity.com/paper/2607.22035/) (2026)

## Abstract (arXiv)

Generative AI models, renowned for their ability to synthesize high-quality content, have sparked growing concerns over the improper generation of copyright-protected material. While recent studies have proposed various approaches to address copyright issues, the capability of large vision-language models (LVLMs) to detect copyright infringements remains largely unexplored. In this work, we focus on evaluating the copyright detection abilities of state-of-the-art LVLMs using a various set of image samples. Recognizing the absence of a comprehensive dataset that includes both IP-infringement samples and ambiguous non-infringement negative samples, we construct a benchmark dataset comprising positive samples that violate the copyright protection of well-known IP figures, as well as negative samples that resemble these figures but do not raise copyright concerns. This dataset is created using advanced prompt engineering techniques. We then evaluate leading LVLMs using our benchmark dataset. Our experimental results reveal that LVLMs are prone to overfitting, leading to the misclassification of some negative samples as IP-infringement cases. In the final section, we analyze these failure cases and propose potential solutions to mitigate the overfitting problem.