HE-OFT: Privacy-Preserving One-Shot Federated Fine-Tuning under Homomorphic Encryption
cs.CR, cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Comments: Technical report. 32 pages, 7 figures, 12 tables. Code: https://github.com/CRYPTO-KU/HE-OFT
Code: https://github.com/CRYPTO-KU/HE-OFT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On the Opportunities and Risks of Foundation Models
- Offsite-Tuning: Transfer Learning without Full Model
- One-Shot Federated Learning
- Revisiting Federated Fine-Tuning: A Single Communication Round is Enough for Foundation Models
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Reconstructing Training Data From Real World Models Trained with Transfer Learning
- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
- FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs
- A Training Framework for Optimal and Stable Training of Polynomial Neural Networks
- Privacy-Preserving CNN Training with Transfer Learning: Two Hidden Layers
- PrivTuner with Homomorphic Encryption and LoRA: A P3EFT Scheme for Privacy-Preserving Parameter-Efficient Fine-Tuning of AI Foundation Models
- Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption
- PUMA: Secure Inference of LLaMA-7B in Five Minutes
- Efficient Decoding Methods for Language Models on Encrypted Data
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs