# Extracted BERT Model Leaks More Information than You Think!

arXiv: https://arxiv.org/abs/2210.11735 · HTML: https://mlsanity.com/paper/2210.11735/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2022.

## Built on by (most cited first, 3 of 3)

- [Training Data Extraction From Pre-trained Language Models: A Survey](https://mlsanity.com/paper/2305.16157/) (2023)
- [Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?](https://mlsanity.com/paper/2307.16382/) (2023)
- [IDT: Dual-Task Adversarial Attacks for Privacy Protection](https://mlsanity.com/paper/2406.19642/) (2024)

## Abstract (arXiv)

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 re mote 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.