The reviewed record of science sign in
Pith

arxiv: 2410.02486 · v2 · pith:YVPBW7ZB · submitted 2024-10-03 · cs.CR · cs.LG

Encryption-Friendly LLM Architecture

Donghwan Rho , Taeseong Kim , Minje Park , Jung Woo Kim , Hyunsik Chae , Ernest K. Ryu , Jung Hee Cheon This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:YVPBW7ZBrecord.jsonopen to challenge →

classification cs.CR cs.LG
keywords fine-tuningarchitecturecomputationalinferencellmsmodelspersonalizedprivacy-preserving
0
0 comments X
read the original abstract

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-preserving machine learning (PPML). However, the computational intensity of transformers poses challenges for applying HE to LLMs. In this work, we propose a modified HE-friendly transformer architecture with an emphasis on inference following personalized (private) fine-tuning. Utilizing LoRA fine-tuning and Gaussian kernels, we achieve significant computational speedups -- 6.94x for fine-tuning and 2.3x for inference -- while maintaining performance comparable to plaintext models. Our findings provide a viable proof of concept for offering privacy-preserving LLM services in areas where data protection is crucial. Our code is available on GitHub.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Probing Memorization of Tabular In-Context Learning

    cs.LG 2026-06 unverdicted novelty 7.0

    A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under rea...

  2. Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models

    cs.CL 2026-06 unverdicted novelty 4.0

    HERALD selectively encrypts sensitive tokens via medical NER, POS policies, and deterministic ciphertext substitution to enable privacy-preserving clinical LLM use while recovering near-plaintext task performance.