相关论文: The Text Anonymization Benchmark (TAB): A Dedicate…

Text anonymization is the process of removing or obfuscating information from textual data to protect the privacy of individuals. This process inherently involves a complex trade-off between privacy protection and information preservation,…

Text sanitization is the task of redacting a document to mask all occurrences of (direct or indirect) personal identifiers, with the goal of concealing the identity of the individual(s) referred in it. In this paper, we consider a two-step…

The proliferation of textual data containing sensitive personal information across various domains requires robust anonymization techniques to protect privacy and comply with regulations, while preserving data usability for diverse and…

Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation varies with the data domain, privacy objectives, and downstream application. However, existing…

Data containing personal information is increasingly used to train, fine-tune, or query Large Language Models (LLMs). Text is typically scrubbed of identifying information prior to use, often with tools such as Microsoft's Presidio or…

We propose a novel method to bootstrap text anonymization models based on distant supervision. Instead of requiring manually labeled training data, the approach relies on a knowledge graph expressing the background information assumed to be…

For sensitive text data to be shared among NLP researchers and practitioners, shared documents need to comply with data protection and privacy laws. There is hence a growing interest in automated approaches for text anonymization. However,…

In this work, we aim to clarify and reconcile metrics for evaluating privacy protection in text through a systematic survey. Although text anonymization is essential for enabling NLP research and model development in domains with sensitive…

In this work, we address the problem of text anonymization where the goal is to prevent adversaries from correctly inferring private attributes of the author, while keeping the text utility, i.e., meaning and semantics. We propose…

The collection and use of personal data are becoming more common in today's data-driven culture. While there are many advantages to this, including better decision-making and service delivery, it also poses significant ethical issues around…

The increased use of text data in social science research has benefited from easy-to-access data (e.g., Twitter). That trend comes at the cost of research requiring sensitive but hard-to-share data (e.g., interview data, police reports,…

Text sanitization aims to rewrite parts of a document to prevent disclosure of personal information. The central challenge of text sanitization is to strike a balance between privacy protection (avoiding the leakage of personal information)…

Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are…

The widespread exchange of digital documents in various domains has resulted in abundant private information being shared. This proliferation necessitates redaction techniques to protect sensitive content and user privacy. While numerous…

This work introduces an anonymization scheme for a corpus of texts to safeguard metadata from disclosure. It specifically aims to prevent large language models from identifying metadata associated with texts, thereby avoiding their…

In the realm of data privacy, the ability to effectively anonymise text is paramount. With the proliferation of deep learning and, in particular, transformer architectures, there is a burgeoning interest in leveraging these advanced models…

Authorship obfuscation techniques hold the promise of helping people protect their privacy in online communications by automatically rewriting text to hide the identity of the original author. However, obfuscation has been evaluated in…

Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence…

Current text anonymization evaluation relies on span-based metrics that fail to capture what an adversary could actually infer, and assumes a single data subject, ignoring multi-subject scenarios. To address these limitations, we present…

Privacy and security are major concerns when communicating speech signals to cloud services such as automatic speech recognition (ASR) and speech emotion recognition (SER). Existing solutions for speech anonymization mainly focus on voice…