ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods

Roy Xie, Junlin Wang, Ruomin Huang, Minxing Zhang, Rong Ge, Jian Pei, Neil Zhenqiang Gong, Bhuwan Dhingra


Abstract
The rapid scaling of large language models (LLMs) has raised concerns about the transparency and fair use of the data used in their pretraining. Detecting such content is challenging due to the scale of the data and limited exposure of each instance during training. We propose ReCaLL (Relative Conditional Log-Likelihood), a novel membership inference attack (MIA) to detect LLMs’ pretraining data by leveraging their conditional language modeling capabilities. ReCaLL examines the relative change in conditional log-likelihoods when prefixing target data points with non-member context. Our empirical findings show that conditioning member data on non-member prefixes induces a larger decrease in log-likelihood compared to non-member data. We conduct comprehensive experiments and show that ReCaLL achieves state-of-the-art performance on the WikiMIA dataset, even with random and synthetic prefixes, and can be further improved using an ensemble approach. Moreover, we conduct an in-depth analysis of LLMs’ behavior with different membership contexts, providing insights into how LLMs leverage membership information for effective inference at both the sequence and token level.
Anthology ID:
2024.emnlp-main.493
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8671–8689
Language:
URL:
https://aclanthology.org/2024.emnlp-main.493
DOI:
10.18653/v1/2024.emnlp-main.493
Bibkey:
Cite (ACL):
Roy Xie, Junlin Wang, Ruomin Huang, Minxing Zhang, Rong Ge, Jian Pei, Neil Zhenqiang Gong, and Bhuwan Dhingra. 2024. ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8671–8689, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods (Xie et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.493.pdf