Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models

2023/12/12 by Sheng Zhang, Hui Li, Zhang, Sheng +1 · 2 citations
Computer Science · #FOS: Computer and information sciences #Software Engineering (cs.SE) #Software Engineering Research

paper · pdf · doi:10.48550/arxiv.2312.07200

openalex publication_date 2023/12/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Effective Code Membership Inference for Code Completion Models via Adversarial Prompts
• LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

Related

• Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach
• How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?
• RepoMark: A Data-Usage Auditing Framework for Code Large Language Models
• The "code'' of Ethics:A Holistic Audit of AI Code Generators
• CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings