Venue
- EMNLP 2022
Date
- 2022
Share
Extracted BERT Model Leaks More Information than You Think!
Xuanli He*
Chen Chen
Qiongkai Xu*
* External authors
EMNLP 2022
2022
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.
Related Publications
Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally indicate more privacy leakage. Image…
With growing concerns regarding privacy in machine learning models, regulations have committed to granting individuals the right to be forgotten while mandating companies to develop non-discriminatory machine learning systems, thereby fueling the study of the machine unlearn…
This paper focuses on addressing the practical yet challenging problem of model heterogeneity in federated learning, where clients possess models with different network structures. To track this problem, we propose a novel framework called pFedHR, which leverages heterogeneo…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
