2022 · 42 citations · 15 references
ComputingComputer ScienceCybersecurityComputer SecurityMachine LearningNatural Language ProcessingData ProtectionLanguage ModelingLanguage ModelsFine-tuningFull Model ApproachLanguage Model Fine-tuningLanguage Model PretrainingMembership InferenceMembership Inference AttacksMembership Inference RiskPrivacy-preserving Machine Learning
Large language models are shown to present privacy risks through memorization of training data, andseveral recent works have studied such risks for the pre-training phase. Little attention, however, has been given to the fine-tuning phase and it is not well understood how different fine-tuning methods (such as fine-tuning the full model, the model head, and adapter) compare in terms of memorization risk. This presents increasing concern as the "pre-train and fine-tune" paradigm proliferates. In this paper, we empirically study memorization of fine-tuning methods using membership inference and extraction attacks, and show that their susceptibility to attacks is very different. We observe that fine-tuning the head of the model has the highest susceptibility to attacks, whereas fine-tuning smaller adapters appears to be less vulnerable to known extraction attacks.
15
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Xiang Lisa Li, Percy Liang · 2021 · 2.2K citations · Full text
Evaluating Large Language Models Trained on Code
arXiv (Cornell University) · 2021 · 1.4K citations · Full text