Papers Text Anonymization
“Text Anonymization” 태그가 달린 논문 23편 · 필터 해제
AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text
In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization…
Contrastive LearningLanguage ModelingLanguage ModellingLarge Language Model+1Learning Extrapolative Sequence Transformations from Markov Chains
Most successful applications of deep learning involve similar training and test conditions. However, tasks such as biological sequence design involve searching for sequences that improve desirable properties beyond previ…
Text AnonymizationA document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court
Topic modeling in Italian legal research is hindered by the lack of public datasets, limiting the analysis of legal themes in Supreme Court judgments. To address this, we developed a document processing pipeline that pro…
DiversityDocument Layout AnalysisOptical Character RecognitionOptical Character Recognition (OCR)+1Survey of Pseudonymization, Abstractive Summarization & Spell Checker for Hindi and Marathi
India's vast linguistic diversity presents unique challenges and opportunities for technological advancement, especially in the realm of Natural Language Processing (NLP). While there has been significant progress in NLP…
Abstractive Text SummarizationDiversityText AnonymizationText SummarizationTruthful Text Sanitization Guided by Inference Attacks
The purpose of text sanitization is to rewrite those text spans in a document that may directly or indirectly identify an individual, to ensure they no longer disclose personal information. Text sanitization must strike …
Text AnonymizationDIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization
Sharing protected health information (PHI) is critical for furthering biomedical research. Before data can be distributed, practitioners often perform deidentification to remove any PHI contained in the text. Contemporar…
De-identificationLanguage ModelingLanguage ModellingLarge Language Model+1Robust Utility-Preserving Text Anonymization Based on Large Language Models
Text anonymization is crucial for sharing sensitive data while maintaining privacy. Existing techniques face the emerging challenges of re-identification attack ability of Large Language Models (LLMs), which have shown a…
Text AnonymizationIncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
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. …
AttributeText AnonymizationComparing Feature-based and Context-aware Approaches to PII Generalization Level Prediction
Protecting Personal Identifiable Information (PII) in text data is crucial for privacy, but current PII generalization methods face challenges such as uneven data distributions and limited context awareness. To address t…
Ensemble Learningfeature selectionText AnonymizationUnlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study
Automated clinical text anonymization has the potential to unlock the widespread sharing of textual health data for secondary usage while assuring patient privacy and safety. Despite the proposal of many complex and theo…
Text AnonymizationLarge Language Models are Advanced Anonymizers
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 anonym…
Text AnonymizationNeural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis
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 …
Language Modellingnamed-entity-recognitionNamed Entity RecognitionText AnonymizationBeyond Memorization: Violating Privacy Via Inference with Large Language Models
Current privacy research on large language models (LLMs) primarily focuses on the issue of extracting memorized training data. At the same time, models' inference capabilities have increased drastically. This raises the …
MemorizationText AnonymizationHengam: An Adversarially Trained Transformer for Persian Temporal Tagging
Many NLP main tasks benefit from an accurate understanding of temporal expressions, e.g., text summarization, question answering, and information retrieval. This paper introduces Hengam, an adversarially trained transfor…
Information RetrievalNamed Entity Recognition (NER)Question AnsweringRetrieval+3Bootstrapping Text Anonymization Models with Distant Supervision
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 infor…
Language ModelingLanguage ModellingText AnonymizationThe Limits of Word Level Differential Privacy
As the issues of privacy and trust are receiving increasing attention within the research community, various attempts have been made to anonymize textual data. A significant subset of these approaches incorporate differe…
SentenceText AnonymizationWord EmbeddingsThe Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization
We present a novel benchmark and associated evaluation metrics for assessing the performance of text anonymization methods. Text anonymization, defined as the task of editing a text document to prevent the disclosure of …
De-identificationText AnonymizationFew-shot Controllable Style Transfer for Low-Resource Multilinugal Settings
Style transfer is the task of rewriting an input sentence into a target style while approximately preserving its content. While most prior literature assumes access to large style-labelled corpora, recent work (Riley et …
AttributeSentenceStyle TransferText Anonymization+1Bootstrapping Text Anonymization Models with Distant Supervision
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 info…
Language ModelingLanguage ModellingText AnonymizationFew-shot Controllable Style Transfer for Low-Resource Multilingual Settings
Style transfer is the task of rewriting a sentence into a target style while approximately preserving content. While most prior literature assumes access to a large style-labelled corpus, recent work (Riley et al. 2021) …
AttributeSentenceStyle TransferText Anonymization+1