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

arXiv:2405.09805v1 Announce Type: new
Abstract: Traditional security mechanisms isolate resources from users who should not access them. 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. Other approaches to LLM safety attempt to protect against bad actors or bad outcomes, but can only do so to an extent making them inappropriate for sensitive data. SecureLLM blends access security with fine-tuning methods. Each data silo …

abstract access arxiv build cs.cl cs.cr data language language models llm llms nature resources secret security them type