CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914717860102144 |
|---|---|
| author | Wu, Xiaoyu Hua, Yang Liang, Chumeng Zhang, Jiaru Wang, Hao Song, Tao Guan, Haibing |
| author_facet | Wu, Xiaoyu Hua, Yang Liang, Chumeng Zhang, Jiaru Wang, Hao Song, Tao Guan, Haibing |
| contents | Diffusion Models (DMs) have evolved into advanced image generation tools, especially for few-shot generation where a pretrained model is fine-tuned on a small set of images to capture a specific style or object. Despite their success, concerns exist about potential copyright violations stemming from the use of unauthorized data in this process. In response, we present Contrasting Gradient Inversion for Diffusion Models (CGI-DM), a novel method featuring vivid visual representations for digital copyright authentication. Our approach involves removing partial information of an image and recovering missing details by exploiting conceptual differences between the pretrained and fine-tuned models. We formulate the differences as KL divergence between latent variables of the two models when given the same input image, which can be maximized through Monte Carlo sampling and Projected Gradient Descent (PGD). The similarity between original and recovered images serves as a strong indicator of potential infringements. Extensive experiments on the WikiArt and Dreambooth datasets demonstrate the high accuracy of CGI-DM in digital copyright authentication, surpassing alternative validation techniques. Code implementation is available at https://github.com/Nicholas0228/Revelio. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11162 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion Wu, Xiaoyu Hua, Yang Liang, Chumeng Zhang, Jiaru Wang, Hao Song, Tao Guan, Haibing Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security Computers and Society Machine Learning Diffusion Models (DMs) have evolved into advanced image generation tools, especially for few-shot generation where a pretrained model is fine-tuned on a small set of images to capture a specific style or object. Despite their success, concerns exist about potential copyright violations stemming from the use of unauthorized data in this process. In response, we present Contrasting Gradient Inversion for Diffusion Models (CGI-DM), a novel method featuring vivid visual representations for digital copyright authentication. Our approach involves removing partial information of an image and recovering missing details by exploiting conceptual differences between the pretrained and fine-tuned models. We formulate the differences as KL divergence between latent variables of the two models when given the same input image, which can be maximized through Monte Carlo sampling and Projected Gradient Descent (PGD). The similarity between original and recovered images serves as a strong indicator of potential infringements. Extensive experiments on the WikiArt and Dreambooth datasets demonstrate the high accuracy of CGI-DM in digital copyright authentication, surpassing alternative validation techniques. Code implementation is available at https://github.com/Nicholas0228/Revelio. |
| title | CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2403.11162 |