← Search

Taeseong Kim

1 accepted papers

2025

Encryption-Friendly LLM Architecture

ICLR 2025poster

Large language models (LLMs) offer personalized responses based on user interactions, but this use case raises serious privacy concerns. Homomorphic encryption (HE) is a cryptographic protocol supporting arithmetic computations in encrypted states and provides a potential solution for privacy-preser…

Cited by 6SourcePDFScholar