Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models

Jeffrey Cheng, Ruoxi Jia

Abstract

Develops precise methods for detecting and extracting training data from LLMs when white-box access is available, with implications for copyright and privacy.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400043,
  title = {Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models},
  author = {Jeffrey Cheng and Ruoxi Jia},
  year = {2024},
  journal = {arXiv preprint},
  url = {https://arxiv.org/abs/2402.17012},
}