Who Wrote this Code? Watermarking for Code Generation
Taehyun Lee, Seokhee Hong, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin, Gunhee Kim
Abstract
Since the remarkable generation performance of large language models raised ethical and legal concerns, approaches to detect machine-generated text by embedding watermarks are being developed.However, we discover that the existing works fail to function appropriately in code generation tasks due to the task’s nature of having low entropy.Extending a logit-modifying watermark method, we propose Selective WatErmarking via Entropy Thresholding (SWEET), which enhances detection ability and mitigates code quality degeneration by removing low-entropy segments at generating and detecting watermarks.Our experiments show that SWEET significantly improves code quality preservation while outperforming all baselines, including post-hoc detection methods, in detecting machine-generated code text.Our code is available inhttps://github.com/hongcheki/sweet-watermark.- Anthology ID:
- 2024.acl-long.268
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4890–4911
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.268
- DOI:
- 10.18653/v1/2024.acl-long.268
- Cite (ACL):
- Taehyun Lee, Seokhee Hong, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin, and Gunhee Kim. 2024. Who Wrote this Code? Watermarking for Code Generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4890–4911, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Who Wrote this Code? Watermarking for Code Generation (Lee et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.268.pdf