LoRA fine-tuned language models are vulnerable to membership inference, and using the public pre-trained model as a reference raises attack AUC to 0.775 even in a conservative three-epoch setting.
AstroLLaMA: Towards specialized foundation models in astronomy,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
LoRA fine-tuned language models are vulnerable to membership inference, and using the public pre-trained model as a reference raises attack AUC to 0.775 even in a conservative three-epoch setting.