A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication
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_ | 1866916991124635648 |
|---|---|
| author | Deng, Jingyi Lin, Chenhao Zhao, Zhengyu Liu, Shuai Peng, Zhe Wang, Qian Shen, Chao |
| author_facet | Deng, Jingyi Lin, Chenhao Zhao, Zhengyu Liu, Shuai Peng, Zhe Wang, Qian Shen, Chao |
| contents | Deep generative models have demonstrated impressive performance in various computer vision applications, including image synthesis, video generation, and medical analysis. Despite their significant advancements, these models may be used for malicious purposes, such as misinformation, deception, and copyright violation. In this paper, we provide a systematic and timely review of research efforts on defenses against AI-generated visual media, covering detection, disruption, and authentication. We review existing methods and summarize the mainstream defense-related tasks within a unified passive and proactive framework. Moreover, we survey the derivative tasks concerning the trustworthiness of defenses, such as their robustness and fairness. For each defense strategy, we formulate its general pipeline and propose a multidimensional taxonomy applicable across defense tasks, based on methodological strategies. Additionally, we summarize the commonly used evaluation datasets, criteria, and metrics. Finally, by analyzing the reviewed studies, we provide insights into current research challenges and suggest possible directions for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10575 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication Deng, Jingyi Lin, Chenhao Zhao, Zhengyu Liu, Shuai Peng, Zhe Wang, Qian Shen, Chao Computer Vision and Pattern Recognition Deep generative models have demonstrated impressive performance in various computer vision applications, including image synthesis, video generation, and medical analysis. Despite their significant advancements, these models may be used for malicious purposes, such as misinformation, deception, and copyright violation. In this paper, we provide a systematic and timely review of research efforts on defenses against AI-generated visual media, covering detection, disruption, and authentication. We review existing methods and summarize the mainstream defense-related tasks within a unified passive and proactive framework. Moreover, we survey the derivative tasks concerning the trustworthiness of defenses, such as their robustness and fairness. For each defense strategy, we formulate its general pipeline and propose a multidimensional taxonomy applicable across defense tasks, based on methodological strategies. Additionally, we summarize the commonly used evaluation datasets, criteria, and metrics. Finally, by analyzing the reviewed studies, we provide insights into current research challenges and suggest possible directions for future research. |
| title | A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.10575 |