# Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption

arXiv: https://arxiv.org/abs/2505.07329 · HTML: https://mlsanity.com/paper/2505.07329/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 12 May 2025.

## Builds on (most cited first, 10 of 10)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data](https://mlsanity.com/paper/1911.07101/) (2019)
- [PrivateLoRA For Efficient Privacy Preserving LLM](https://mlsanity.com/paper/2311.14030/) (2023)
- [DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model](https://mlsanity.com/paper/2404.05182/) (2024)
- [PackVFL: Efficient HE Packing for Vertical Federated Learning](https://mlsanity.com/paper/2405.00482/) (2024)

## Built on by (most cited first, 7 of 7)

- [Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments](https://mlsanity.com/paper/2506.23706/) (2025)
- [Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey](https://mlsanity.com/paper/2510.12178/) (2025)
- [Key-Conditioned Orthonormal Transform Gating (K-OTG): Multi-Key Access Control with Hidden-State Scrambling for LoRA-Tuned Models](https://mlsanity.com/paper/2512.17519/) (2025)
- [Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption](https://mlsanity.com/paper/2604.23245/) (2026)
- [CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts](https://mlsanity.com/paper/2609.35883/) (2026)
- [DP-ES: Differentially Private Evolution Strategies for Prompt Optimization](https://mlsanity.com/paper/2610.06236/) (2026)
- [HE-OFT: Privacy-Preserving One-Shot Federated Fine-Tuning under Homomorphic Encryption](https://mlsanity.com/paper/2610.08255/) (2026)

## Abstract (arXiv)

Preserving data confidentiality during the fine-tuning of open-source Large Language Models (LLMs) is crucial for sensitive applications. This work introduces an interactive protocol adapting the Low-Rank Adaptation (LoRA) technique for private fine-tuning. Homomorphic Encryption (HE) protects the confidentiality of training data and gradients handled by remote worker nodes performing the bulk of computations involving the base model weights. The data owner orchestrates training, requiring minimal local computing power and memory, thus alleviating the need for expensive client-side GPUs. We demonstrate feasibility by fine-tuning a Llama-3.2-1B model, presenting convergence results using HE-compatible quantization and performance benchmarks for HE computations on GPU hardware. This approach enables applications such as confidential knowledge base question answering, private codebase fine-tuning for AI code assistants, AI agents for drafting emails based on a company's email archive, and adapting models to analyze sensitive legal or healthcare documents.