Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2406.03728 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913380059578368 |
|---|---|
| author | Qiu, Jielin Han, William Zhao, Xuandong Long, Shangbang Faloutsos, Christos Li, Lei |
| author_facet | Qiu, Jielin Han, William Zhao, Xuandong Long, Shangbang Faloutsos, Christos Li, Lei |
| contents | With the development of large models, watermarks are increasingly employed to assert copyright, verify authenticity, or monitor content distribution. As applications become more multimodal, the utility of watermarking techniques becomes even more critical. The effectiveness and reliability of these watermarks largely depend on their robustness to various disturbances. However, the robustness of these watermarks in real-world scenarios, particularly under perturbations and corruption, is not well understood. To highlight the significance of robustness in watermarking techniques, our study evaluated the robustness of watermarked content generated by image and text generation models against common real-world image corruptions and text perturbations. Our results could pave the way for the development of more robust watermarking techniques in the future. Our project website can be found at \url{https://mmwatermark-robustness.github.io/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03728 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Durability: Benchmark Insights into Multimodal Watermarking Qiu, Jielin Han, William Zhao, Xuandong Long, Shangbang Faloutsos, Christos Li, Lei Computer Vision and Pattern Recognition With the development of large models, watermarks are increasingly employed to assert copyright, verify authenticity, or monitor content distribution. As applications become more multimodal, the utility of watermarking techniques becomes even more critical. The effectiveness and reliability of these watermarks largely depend on their robustness to various disturbances. However, the robustness of these watermarks in real-world scenarios, particularly under perturbations and corruption, is not well understood. To highlight the significance of robustness in watermarking techniques, our study evaluated the robustness of watermarked content generated by image and text generation models against common real-world image corruptions and text perturbations. Our results could pave the way for the development of more robust watermarking techniques in the future. Our project website can be found at \url{https://mmwatermark-robustness.github.io/}. |
| title | Evaluating Durability: Benchmark Insights into Multimodal Watermarking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.03728 |