SecureLLM: Using Compositionality to Build Provably Secure Language Models for Private, Sensitive, and Secret Data

1 code implementation • 16 May 2024 • Abdulrahman Alabdulakreem, Christian M Arnold, Yerim Lee, Pieter M Feenstra, Boris Katz, Andrei Barbu

We reflect the compositional nature of such security mechanisms back into the structure of LLMs to build a provably secure LLM; that we term SecureLLM.

Translation