IP Protection and Privacy in LLM: Leveraging Fully Homomorphic Encryption

Monday, May. 6, 2024
2:20 PM - 3:10 PM PT
Available On Demand
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



Topic/Track
Privacy & Data Protection

Type/Format
Track Session

Session Classification
Advanced - Technical

Pass Requirement
  • CISO BOOT CAMP
  • Cyber Leaders Forum
  • eFraud Global Forum
  • Executive Security Action Forum
  • Full Conference
  • Media: Press/Analyst
  • On Demand
  • Speaker

Session Code
PDP-M06


Share With Your Community