Teach LLMs to Phish: Stealing Private Information from Language Models
Ashwinee Panda, Christopher A. Choquette-Choo, Zhengming Zhang, Yaoqing Yang, Prateek Mittal
Abstract
When large language models are trained on private data, it can be a \textit{significant} privacy risk for them to memorize and regurgitate sensitive information. In this work, we propose a new \emph{practical} data extraction attack that we call ``neural phishing''. This attack enables an adversary to target and extract sensitive or personally identifiable information (PII), e.g., credit card numbers, from a model trained on user data with upwards of $10\%$ attack success rates, at times, as high as $50\%$. Our attack assumes only that an adversary can insert as few as $10$s of benign-appearing sentences into the training dataset using only vague priors on the structure of the user data.
BibTeX
@inproceedings{
panda2024teach,
title={Teach {LLM}s to Phish: Stealing Private Information from Language Models},
author={Ashwinee Panda and Christopher A. Choquette-Choo and Zhengming Zhang and Yaoqing Yang and Prateek Mittal},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=qo21ZlfNu6}
}