On the Vulnerability of Text Sanitization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909600461094912 |
|---|---|
| author | Tong, Meng Chen, Kejiang Yuan, Xiaojian Liu, Jiayang Zhang, Weiming Yu, Nenghai Zhang, Jie |
| author_facet | Tong, Meng Chen, Kejiang Yuan, Xiaojian Liu, Jiayang Zhang, Weiming Yu, Nenghai Zhang, Jie |
| contents | Text sanitization, which employs differential privacy to replace sensitive tokens with new ones, represents a significant technique for privacy protection. Typically, its performance in preserving privacy is evaluated by measuring the attack success rate (ASR) of reconstruction attacks, where attackers attempt to recover the original tokens from the sanitized ones. However, current reconstruction attacks on text sanitization are developed empirically, making it challenging to accurately assess the effectiveness of sanitization. In this paper, we aim to provide a more accurate evaluation of sanitization effectiveness. Inspired by the works of Palamidessi et al., we implement theoretically optimal reconstruction attacks targeting text sanitization. We derive their bounds on ASR as benchmarks for evaluating sanitization performance. For real-world applications, we propose two practical reconstruction attacks based on these theoretical findings. Our experimental results underscore the necessity of reassessing these overlooked risks. Notably, one of our attacks achieves a 46.4% improvement in ASR over the state-of-the-art baseline, with a privacy budget of epsilon=4.0 on the SST-2 dataset. Our code is available at: https://github.com/mengtong0110/On-the-Vulnerability-of-Text-Sanitization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_17052 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Vulnerability of Text Sanitization Tong, Meng Chen, Kejiang Yuan, Xiaojian Liu, Jiayang Zhang, Weiming Yu, Nenghai Zhang, Jie Cryptography and Security Text sanitization, which employs differential privacy to replace sensitive tokens with new ones, represents a significant technique for privacy protection. Typically, its performance in preserving privacy is evaluated by measuring the attack success rate (ASR) of reconstruction attacks, where attackers attempt to recover the original tokens from the sanitized ones. However, current reconstruction attacks on text sanitization are developed empirically, making it challenging to accurately assess the effectiveness of sanitization. In this paper, we aim to provide a more accurate evaluation of sanitization effectiveness. Inspired by the works of Palamidessi et al., we implement theoretically optimal reconstruction attacks targeting text sanitization. We derive their bounds on ASR as benchmarks for evaluating sanitization performance. For real-world applications, we propose two practical reconstruction attacks based on these theoretical findings. Our experimental results underscore the necessity of reassessing these overlooked risks. Notably, one of our attacks achieves a 46.4% improvement in ASR over the state-of-the-art baseline, with a privacy budget of epsilon=4.0 on the SST-2 dataset. Our code is available at: https://github.com/mengtong0110/On-the-Vulnerability-of-Text-Sanitization. |
| title | On the Vulnerability of Text Sanitization |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2410.17052 |