Privacy Preserving API Fine-tuning for LLMs

[PDF] arxiv.org

PrivTuner with Homomorphic Encryption and LoRA: A P3EFT Scheme for Privacy-Preserving Parameter-Efficient Fine-Tuning of AI Foundation Models

Y Li, W Yu, J Zhao - arXiv preprint arXiv:2410.00433, 2024 - arxiv.org
AI foundation models have recently demonstrated impressive capabilities across a wide
range of tasks. Fine-tuning (FT) is a method of customizing a pre-trained AI foundation …
相关文章 所有 2 个版本