paper-with-me

Papers

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage

2025-04-28 · Rui Xin, Niloofar Mireshghallah, Shuyue Stella Li, Michael Duan, Hyunwoo Kim, Yejin Choi, Yulia Tsvetkov, Sewoong Oh, Pang Wei Koh

Sanitizing sensitive text data typically involves removing personally identifiable information (PII) or generating synthetic data under the assumption that these methods adequately protect privacy; however, their effectiveness is often only assessed by measuring the leakage of explicit identifiers but ignoring nuanced textual markers that can lead to re-identification. We challenge the above illusion of privacy by proposing a new framework that evaluates re-identification attacks to quantify individual privacy risks upon data release. Our approach shows that seemingly innocuous auxiliary information -- such as routine social activities -- can be used to infer sensitive attributes like age or substance use history from sanitized data. For instance, we demonstrate that Azure's commercial PII removal tool fails to protect 74\% of information in the MedQA dataset. Although differential privacy mitigates these risks to some extent, it significantly reduces the utility of the sanitized text for downstream tasks. Our findings indicate that current sanitization techniques offer a \textit{false sense of privacy}, highlighting the need for more robust methods that protect against semantic-level information leakage.

📄 PDF Abstract BibTeX arXiv:2504.21035

Code (0)

등록된 구현이 없습니다.

Tasks

MedQA

Similar Papers 제목 키워드 기반

Textual Unlearning Gives a False Sense of Unlearning

2024-06-19 · Jiacheng Du, Zhibo Wang, Jie Zhang, Xiaoyi Pang 외

Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information. To mitigate privacy risks and safeguard the right to be forgotten, machine unlearning has emerged as a pr…

Machine Unlearning

Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings

2022-03-14 · Yi Zhou, Masahiro Kaneko, Danushka Bollegala

Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to …

Word Embeddings

Sense Embeddings are also Biased – Evaluating Social Biases in Static and Contextualised Sense Embeddings

2022-05-01 · ACL 2022 5 · Yi Zhou, Masahiro Kaneko, Danushka Bollegala

Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to …

Word Embeddings

Sense Embeddings are also Biased -- Evaluating Social Biases in Static and Contextualised Sense Embeddings

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to …

Word Embeddings

Privacy issues on biometric systems

2022-02-23 · Marcos Faundez-Zanuy

In the XXIth century there is a strong interest on privacy issues. Technology permits obtaining personal information without individuals consent, computers make it feasible to share and process this information, and this…