Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908972275990528 |
|---|---|
| author | Li, Guo Chen, Weihong Fan, Yongfu |
| author_facet | Li, Guo Chen, Weihong Fan, Yongfu |
| contents | Diffusion models have demonstrated powerful performance in generating high-quality images. A typical example is text-to-image generator like Stable Diffusion. However, their widespread use also poses potential privacy risks. A key concern is membership inference attacks, which attempt to determine whether a particular data sample was used in the model training process. Existing membership inference attacks against diffusion models either directly exploit sample loss differences or rely on image-level reconstruction differences. Both approaches commonly ignore the consistency characteristics of noise prediction during the diffusion process, resulting in either low inference accuracy or high computational costs. To address these shortcomings, we propose a membership inference method based on noise aggregation analysis, and introduce a single-step, low-intensity noise injection diffusion strategy to amplify differences between member and non-member samples. Our proposed approach substantially reduces model query requirements while delivering more efficient and accurate membership inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21783 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models Li, Guo Chen, Weihong Fan, Yongfu Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security Diffusion models have demonstrated powerful performance in generating high-quality images. A typical example is text-to-image generator like Stable Diffusion. However, their widespread use also poses potential privacy risks. A key concern is membership inference attacks, which attempt to determine whether a particular data sample was used in the model training process. Existing membership inference attacks against diffusion models either directly exploit sample loss differences or rely on image-level reconstruction differences. Both approaches commonly ignore the consistency characteristics of noise prediction during the diffusion process, resulting in either low inference accuracy or high computational costs. To address these shortcomings, we propose a membership inference method based on noise aggregation analysis, and introduce a single-step, low-intensity noise injection diffusion strategy to amplify differences between member and non-member samples. Our proposed approach substantially reduces model query requirements while delivering more efficient and accurate membership inference. |
| title | Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2510.21783 |