Identity-Focused Inference and Extraction Attacks on Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910648867225600 |
|---|---|
| author | Vora, Jayneel Krishnan, Aditya Bouacida, Nader Shankar, Prabhu RV Mohapatra, Prasant |
| author_facet | Vora, Jayneel Krishnan, Aditya Bouacida, Nader Shankar, Prabhu RV Mohapatra, Prasant |
| contents | The increasing reliance on diffusion models for generating synthetic images has amplified concerns about the unauthorized use of personal data, particularly facial images, in model training. In this paper, we introduce a novel identity inference framework to hold model owners accountable for including individuals' identities in their training data. Our approach moves beyond traditional membership inference attacks by focusing on identity-level inference, providing a new perspective on data privacy violations. Through comprehensive evaluations on two facial image datasets, Labeled Faces in the Wild (LFW) and CelebA, our experiments demonstrate that the proposed membership inference attack surpasses baseline methods, achieving an attack success rate of up to 89% and an AUC-ROC of 0.91, while the identity inference attack attains 92% on LDM models trained on LFW, and the data extraction attack achieves 91.6% accuracy on DDPMs, validating the effectiveness of our approach across diffusion models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10177 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Identity-Focused Inference and Extraction Attacks on Diffusion Models Vora, Jayneel Krishnan, Aditya Bouacida, Nader Shankar, Prabhu RV Mohapatra, Prasant Computer Vision and Pattern Recognition Cryptography and Security Machine Learning The increasing reliance on diffusion models for generating synthetic images has amplified concerns about the unauthorized use of personal data, particularly facial images, in model training. In this paper, we introduce a novel identity inference framework to hold model owners accountable for including individuals' identities in their training data. Our approach moves beyond traditional membership inference attacks by focusing on identity-level inference, providing a new perspective on data privacy violations. Through comprehensive evaluations on two facial image datasets, Labeled Faces in the Wild (LFW) and CelebA, our experiments demonstrate that the proposed membership inference attack surpasses baseline methods, achieving an attack success rate of up to 89% and an AUC-ROC of 0.91, while the identity inference attack attains 92% on LDM models trained on LFW, and the data extraction attack achieves 91.6% accuracy on DDPMs, validating the effectiveness of our approach across diffusion models. |
| title | Identity-Focused Inference and Extraction Attacks on Diffusion Models |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2410.10177 |