Stealing Part of a Production LLM | API protect LLMs no more

How it is possible to steal part of LLMs protected behind an API? 🥷 We explain both papers that made a breakthrough on this, one from Carlini et al. (Google), and the other one from Finlayson et al. (USC), see references below.
SPONSOR: AssemblyAI 👉 https://www.assemblyai.com/research/universal-1/?utm_source=youtube&utm_medium=social&utm_campaign=universal1_letitia

AI Coffee Break Merch! 🛍️ https://aicoffeebreak.creator-spring.com/

📄 Carlini, Nicholas, Daniel Paleka, Krishnamurthy Dj Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee et al. "Stealing Part of a Production Language Model." https://arxiv.org/abs/2403.06634
📄 …

api google llm llms papers part production protect stealing support usc