Published June 7, 2025
| Version v1
Dataset
Open
PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty
Creators
Description
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.
Files
privacyxray.zip
Files
(27.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:26cf7963e2e3d091e06f7770edc8b0d3
|
27.1 MB | Preview Download |