Differentially private fine-tuning sharply reduces both data-extraction and membership-inference risk on GPT-2 models, while full fine-tuning and LoRA preserve utility best.
In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics
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
-
Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?
Differentially private fine-tuning sharply reduces both data-extraction and membership-inference risk on GPT-2 models, while full fine-tuning and LoRA preserve utility best.