IP Protection and Privacy in LLM: Leveraging Fully Homomorphic Encryption


Posted on in Presentations

Large Language Models (LLMs) are increasingly utilized in various applications. However, there's a dilemma between safeguarding the model owner's assets and ensuring the user's data privacy. This session introduces a hybrid method that employs Fully Homomorphic Encryption to address both these concerns. Presenting a live demonstration of the approach, highlighting its practicality and efficiency.

Participants
Benoit Chevallier-Mames

Speaker

VP of Cloud and Machine Learning, Zama

Jordan Frery

Speaker

Research Scientist, Zama


Share With Your Community