CEFW: A Comprehensive Evaluation Framework for Watermark in Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916663394304000 |
|---|---|
| author | Zhang, Shuhao Cheng, Bo Han, Jiale Chen, Yuli Wu, Zhixuan Li, Changbao Gu, Pingli |
| author_facet | Zhang, Shuhao Cheng, Bo Han, Jiale Chen, Yuli Wu, Zhixuan Li, Changbao Gu, Pingli |
| contents | Text watermarking provides an effective solution for identifying synthetic text generated by large language models. However, existing techniques often focus on satisfying specific criteria while ignoring other key aspects, lacking a unified evaluation. To fill this gap, we propose the Comprehensive Evaluation Framework for Watermark (CEFW), a unified framework that comprehensively evaluates watermarking methods across five key dimensions: ease of detection, fidelity of text quality, minimal embedding cost, robustness to adversarial attacks, and imperceptibility to prevent imitation or forgery. By assessing watermarks according to all these key criteria, CEFW offers a thorough evaluation of their practicality and effectiveness. Moreover, we introduce a simple and effective watermarking method called Balanced Watermark (BW), which guarantees robustness and imperceptibility through balancing the way watermark information is added. Extensive experiments show that BW outperforms existing methods in overall performance across all evaluation dimensions. We release our code to the community for future research. https://github.com/DrankXs/BalancedWatermark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20802 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CEFW: A Comprehensive Evaluation Framework for Watermark in Large Language Models Zhang, Shuhao Cheng, Bo Han, Jiale Chen, Yuli Wu, Zhixuan Li, Changbao Gu, Pingli Cryptography and Security Artificial Intelligence Text watermarking provides an effective solution for identifying synthetic text generated by large language models. However, existing techniques often focus on satisfying specific criteria while ignoring other key aspects, lacking a unified evaluation. To fill this gap, we propose the Comprehensive Evaluation Framework for Watermark (CEFW), a unified framework that comprehensively evaluates watermarking methods across five key dimensions: ease of detection, fidelity of text quality, minimal embedding cost, robustness to adversarial attacks, and imperceptibility to prevent imitation or forgery. By assessing watermarks according to all these key criteria, CEFW offers a thorough evaluation of their practicality and effectiveness. Moreover, we introduce a simple and effective watermarking method called Balanced Watermark (BW), which guarantees robustness and imperceptibility through balancing the way watermark information is added. Extensive experiments show that BW outperforms existing methods in overall performance across all evaluation dimensions. We release our code to the community for future research. https://github.com/DrankXs/BalancedWatermark. |
| title | CEFW: A Comprehensive Evaluation Framework for Watermark in Large Language Models |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2503.20802 |