Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code
CoRR(2024)
摘要
Code auditing ensures that the developed code adheres to standards,
regulations, and copyright protection by verifying that it does not contain
code from protected sources. The recent advent of Large Language Models (LLMs)
as coding assistants in the software development process poses new challenges
for code auditing. The dataset for training these models is mainly collected
from publicly available sources. This raises the issue of intellectual property
infringement as developers' codes are already included in the dataset.
Therefore, auditing code developed using LLMs is challenging, as it is
difficult to reliably assert if an LLM used during development has been trained
on specific copyrighted codes, given that we do not have access to the training
datasets of these models. Given the non-disclosure of the training datasets,
traditional approaches such as code clone detection are insufficient for
asserting copyright infringement. To address this challenge, we propose a new
approach, TraWiC; a model-agnostic and interpretable method based on membership
inference for detecting code inclusion in an LLM's training dataset. We extract
syntactic and semantic identifiers unique to each program to train a classifier
for detecting code inclusion. In our experiments, we observe that TraWiC is
capable of detecting 83.87
comparison, the prevalent clone detection tool NiCad is only capable of
detecting 47.64
resource overhead in contrast to pair-wise clone detection that is conducted
during the auditing process of tools like CodeWhisperer reference tracker,
across thousands of code snippets.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要