Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks

Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, Reza Shokri


Abstract
The wide adoption and application of Masked language models (MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities. Prior attempts at measuring leakage of MLMs via membership inference attacks have been inconclusive, implying potential robustness of MLMs to privacy attacks.In this work, we posit that prior attempts were inconclusive because they based their attack solely on the MLM’s model score. We devise a stronger membership inference attack based on likelihood ratio hypothesis testing that involves an additional reference MLM to more accurately quantify the privacy risks of memorization in MLMs. We show that masked language models are indeed susceptible to likelihood ratio membership inference attacks: Our empirical results, on models trained on medical notes, show that our attack improves the AUC of prior membership inference attacks from 0.66 to an alarmingly high 0.90 level.
Anthology ID:
2022.emnlp-main.570
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8332–8347
Language:
URL:
https://aclanthology.org/2022.emnlp-main.570
DOI:
10.18653/v1/2022.emnlp-main.570
Bibkey:
Cite (ACL):
Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, and Reza Shokri. 2022. Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8332–8347, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks (Mireshghallah et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.570.pdf
Note:
 2022.emnlp-main.570.note.pdf