An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models

Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang, David Evans, Taylor Berg-Kirkpatrick


Abstract
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.
Anthology ID:
2022.emnlp-main.119
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1816–1826
Language:
URL:
https://aclanthology.org/2022.emnlp-main.119
DOI:
Bibkey:
Cite (ACL):
Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang, David Evans, and Taylor Berg-Kirkpatrick. 2022. An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1816–1826, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models (Mireshghallah et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.119.pdf