How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?

Authors: Hua Yang, Alejandro Velasco, Thanh Le-Cong, Md Nazmul Haque, Bowen Xu, Denys Poshyvanyk
Published: 2025-12-17

Source: https://arxiv.org/abs/2512.15468

PDF: https://arxiv.org/pdf/2512.15468

AIにより推定されたラベル

コード変換の因果分析 プライバシー分析 コード難読化

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

The success of large language models for code relies on vast amounts of code data, including public open-source repositories, such as GitHub, and private, confidential code from companies. This raises concerns about intellectual property compliance and the potential unauthorized use of license-restricted code. While membership inference (MI) techniques have been proposed to detect such unauthorized usage, their effectiveness can be undermined by semantically equivalent code transformation techniques, which modify code syntax while preserving semantic. In this work, we systematically investigate whether semantically equivalent code transformation rules might be leveraged to evade MI detection. The results reveal that model accuracy drops by only 1.5