Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.22723 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916972912967680 |
|---|---|
| author | Wei, Kang Yuan, Xin Huo, Fushuo Ma, Chuan Yuan, Long Li, Songze Ding, Ming Tao, Dacheng |
| author_facet | Wei, Kang Yuan, Xin Huo, Fushuo Ma, Chuan Yuan, Long Li, Songze Ding, Ming Tao, Dacheng |
| contents | Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential threats to DMs. To provide advanced and comprehensive insights into safety, ethics, and trust in DMs, this survey comprehensively elucidates its framework, threats, and countermeasures. Each threat and its countermeasures are systematically examined and categorized to facilitate thorough analysis. Furthermore, we introduce specific examples of how DMs are used, what dangers they might bring, and ways to protect against these dangers. Finally, we discuss key lessons learned, highlight open challenges related to DM security, and outline prospective research directions in this critical field. This work aims to accelerate progress not only in the technical capabilities of generative artificial intelligence but also in the maturity and wisdom of its application. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22723 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models Wei, Kang Yuan, Xin Huo, Fushuo Ma, Chuan Yuan, Long Li, Songze Ding, Ming Tao, Dacheng Cryptography and Security Computer Vision and Pattern Recognition Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential threats to DMs. To provide advanced and comprehensive insights into safety, ethics, and trust in DMs, this survey comprehensively elucidates its framework, threats, and countermeasures. Each threat and its countermeasures are systematically examined and categorized to facilitate thorough analysis. Furthermore, we introduce specific examples of how DMs are used, what dangers they might bring, and ways to protect against these dangers. Finally, we discuss key lessons learned, highlight open challenges related to DM security, and outline prospective research directions in this critical field. This work aims to accelerate progress not only in the technical capabilities of generative artificial intelligence but also in the maturity and wisdom of its application. |
| title | Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.22723 |