Stealing Part of a Production Language Model

Nicholas Carlini, Daniel Paleka, Krishnamurthy Dj Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramer

Abstract

Demonstrates that it is possible to steal the embedding projection layer of production LLMs like OpenAI's models through the API, confirming model extraction risks.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400004,
  title = {Stealing Part of a Production Language Model},
  author = {Nicholas Carlini and Daniel Paleka and Krishnamurthy Dj Dvijotham and Thomas Steinke and Jonathan Hayase and A. Feder Cooper and Katherine Lee and Matthew Jagielski and Milad Nasr and Arthur Conmy and Eric Wallace and David Rolnick and Florian Tramer},
  year = {2024},
  journal = {ICML 2024},
  url = {https://arxiv.org/abs/2403.06634},
}