PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty
收藏官方服务：
资源简介：
This artifact contains the code and dataset used in our paper to analyze and classify privacy leakage behaviors in LLMs. It includes scripts for model fine-tuning, hidden state extraction, and classification, as well as training data.
提供机构：
Zenodo创建时间：
2025-06-09
