A client-server protocol uses homomorphic encryption to fine-tune a 1B-parameter LLM with LoRA while keeping training data, activations, and the learned adapter weights hidden from the server.
In: 31st USENIX Security Symposium (USENIX Security 22)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption
A client-server protocol uses homomorphic encryption to fine-tune a 1B-parameter LLM with LoRA while keeping training data, activations, and the learned adapter weights hidden from the server.