He, X; Chen, C; Lyu, L; Xu, Q; (2022) Extracted BERT Model Leaks More Information than You Think! In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022. (pp. pp. 1530-1537). Association for Computational Linguistics: Abu Dhabi, United Arab Emirates.

Preview

Text 2022.emnlp-main.99.pdf - Published Version Download (315kB) | Preview

Abstract

The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning as a service (MLaaS) by encapsulating fine-tuned BERT-based models as APIs. Due to significant commercial interest, there has been a surge of attempts to steal remote services via model extraction. Although previous works have made progress in defending against model extraction attacks, there has been little discussion on their performance in preventing privacy leakage. This work bridges this gap by launching an attribute inference attack against the extracted BERT model. Our extensive experiments reveal that model extraction can cause severe privacy leakage even when victim models are facilitated with advanced defensive strategies.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item