This is the github repository of paper \u300aAn Empirical Study on the Security Vulnerabilities of GPTs\u300b, including the prompts and results mentioned in the paper
Code and instructions to reproduce the manuscript’s figures (Fig 1–Fig 7) from CRFM Ecosystem Graph model metadata (assets.csv). Because the dataset is periodically updated, reruns on later snapshots
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 classif
