Abstract
Code pre-trained language models (CPLMs) have received great attention since they can benefit various tasks that facilitate software development and maintenance. However, CPLMs are trained on massive open-source code, raising concerns about potential data infringement. This paper launches the study of detecting unauthorized code use in CPLMs, i.e., Code Membership Inference (CMI) task. We design a framework Buzzer for different settings of CMI. Buzzer deploys several inference techniques, including signal extraction from pre-training tasks, hard-to-learn sample calibration and weighted inference, to identify code membership status accurately. Extensive experiments show that CMI can be achieved with high accuracy using Buzzer. Hence, Buzzer can serve as a CMI tool and help protect intellectual property rights. The implementation of Buzzer is available at: https://github.com/KDEGroup/Buzzer- Anthology ID:
- 2024.findings-emnlp.621
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10593–10603
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.621/
- DOI:
- 10.18653/v1/2024.findings-emnlp.621
- Cite (ACL):
- Sheng Zhang, Hui Li, and Rongrong Ji. 2024. Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10593–10603, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models (Zhang et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.621.pdf