paper-with-me

홈 › Papers

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

2025-02-23 · Qipan Xu, Zhenting Wang, Xiaoxiao He, Ligong Han, Ruixiang Tang

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.

📄 PDF Abstract BibTeX arXiv:2502.16618

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images

2025-02-23 · YuBo Wang, Jianting Tang, Chaohu Liu, Linli Xu

Large vision-language models (LVLMs) have demonstrated remarkable image understanding and dialogue capabilities, allowing them to handle a variety of visual question answering tasks. However, their widespread availabilit…

Adversarial AttackQuestion AnsweringVisual Question Answering

DIS-CO: Discovering Copyrighted Content in VLMs Training Data

2025-02-24 · André V. Duarte, Xuandong Zhao, Arlindo L. Oliveira, Lei LI

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 …

Language ModelingLanguage Modelling

Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients

2026-06-23 · Zhihao Zhu, Hongyi Tang, Yi Yang, Ahmed Abbasi arxiv

Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in healthcare, where patient medical images paired with…

Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?

2025-12-26 · Naen Xu, Jinghuai Zhang, Changjiang Li, Hengyu An 외 arxiv

Large vision-language models (LVLMs) have achieved remarkable advancements in multimodal reasoning tasks. However, their widespread accessibility raises critical concerns about potential copyright infringement. Will LVLM…

Multimodal Reasoning

CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models

2025-02-21 · Shunchang Liu, Zhuan Shi, Lingjuan Lyu, Yaochu Jin 외

Assessing whether AI-generated images are substantially similar to copyrighted works is a crucial step in resolving copyright disputes. In this paper, we propose CopyJudge, an automated copyright infringement identificat…

Memorization