Model Leeching is a novel extraction attack targeting Large Language Models (LLMs), capable of distilling task-specific knowledge from a target LLM into a reduced parameter model. We demonstrate the effectiveness of our attack by extracting task capability from ChatGPT-3.5-Turbo, achieving 73% Exact Match (EM) similarity, and SQuAD EM and F1 accuracy scores of 75% and 87%, respectively for only $50 in API cost. We further demonstrate the feasibility of adversarial attack transferability from an extracted model extracted via Model Leeching to perform ML attack staging against a target LLM, resulting in an 11% increase to attack success rate when applied to ChatGPT-3.5-Turbo.
@article{arxiv.2309.10544,
title = {Model Leeching: An Extraction Attack Targeting LLMs},
author = {Lewis Birch and William Hackett and Stefan Trawicki and Neeraj Suri and Peter Garraghan},
journal= {arXiv preprint arXiv:2309.10544},
year = {2023}
}