Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929487991537664 |
|---|---|
| author | Pang, Yan Wang, Tianhao |
| author_facet | Pang, Yan Wang, Tianhao |
| contents | With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-quality pre-trained image-generative models, a growing number of users are downloading these pre-trained models to fine-tune them with downstream datasets for various image-generation tasks. However, employing such powerful pre-trained models in downstream tasks presents significant privacy leakage risks. In this paper, we propose the first reconstruction-based membership inference attack framework, tailored for recent diffusion models, and in the more stringent black-box access setting. Considering four distinct attack scenarios and three types of attacks, this framework is capable of targeting any popular conditional generator model, achieving high precision, evidenced by an impressive AUC of $0.95$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_08207 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Black-box Membership Inference Attacks against Fine-tuned Diffusion Models Pang, Yan Wang, Tianhao Cryptography and Security With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-quality pre-trained image-generative models, a growing number of users are downloading these pre-trained models to fine-tune them with downstream datasets for various image-generation tasks. However, employing such powerful pre-trained models in downstream tasks presents significant privacy leakage risks. In this paper, we propose the first reconstruction-based membership inference attack framework, tailored for recent diffusion models, and in the more stringent black-box access setting. Considering four distinct attack scenarios and three types of attacks, this framework is capable of targeting any popular conditional generator model, achieving high precision, evidenced by an impressive AUC of $0.95$. |
| title | Black-box Membership Inference Attacks against Fine-tuned Diffusion Models |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2312.08207 |