A Certified Robust Watermark For Large Language 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_ | 1866917789822877696 |
|---|---|
| author | Feng, Xianheng Liu, Jian Ren, Kui Chen, Chun |
| author_facet | Feng, Xianheng Liu, Jian Ren, Kui Chen, Chun |
| contents | The effectiveness of watermark algorithms in AI-generated text identification has garnered significant attention. Concurrently, an increasing number of watermark algorithms have been proposed to enhance the robustness against various watermark attacks. However, these watermark algorithms remain susceptible to adaptive or unseen attacks. To address this issue, to our best knowledge, we propose the first certified robust watermark algorithm for large language models based on randomized smoothing, which can provide provable guarantees for watermarked text. Specifically, we utilize two different models respectively for watermark generation and detection and add Gaussian and Uniform noise respectively in the embedding and permutation space during the training and inference stages of the watermark detector to enhance the certified robustness of our watermark detector and derive certified radius. To evaluate the empirical robustness and certified robustness of our watermark algorithm, we conducted comprehensive experiments. The results indicate that our watermark algorithm shows comparable performance to baseline algorithms while our algorithm can derive substantial certified robustness, which means that our watermark can not be removed even under significant alterations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19708 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Certified Robust Watermark For Large Language Models Feng, Xianheng Liu, Jian Ren, Kui Chen, Chun Cryptography and Security The effectiveness of watermark algorithms in AI-generated text identification has garnered significant attention. Concurrently, an increasing number of watermark algorithms have been proposed to enhance the robustness against various watermark attacks. However, these watermark algorithms remain susceptible to adaptive or unseen attacks. To address this issue, to our best knowledge, we propose the first certified robust watermark algorithm for large language models based on randomized smoothing, which can provide provable guarantees for watermarked text. Specifically, we utilize two different models respectively for watermark generation and detection and add Gaussian and Uniform noise respectively in the embedding and permutation space during the training and inference stages of the watermark detector to enhance the certified robustness of our watermark detector and derive certified radius. To evaluate the empirical robustness and certified robustness of our watermark algorithm, we conducted comprehensive experiments. The results indicate that our watermark algorithm shows comparable performance to baseline algorithms while our algorithm can derive substantial certified robustness, which means that our watermark can not be removed even under significant alterations. |
| title | A Certified Robust Watermark For Large Language Models |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2409.19708 |