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

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

Framework mappings

@misc{wang2024pandoras,
  title = {{Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models}},
  author = {Jeffrey G. Wang and Jason Wang and Marvin Li and Seth Neel},
  year = {2024},
  eprint = {2402.17012},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.17012}
}