{"total":24,"rows":[{"id":"2202.00443","title":"The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization","created":"2022-01-25","cited_by_count":95,"area":null},{"id":"2309.11852","title":"Knowledge Sanitization of Large Language Models","created":"2023-09-21","cited_by_count":37,"area":null},{"id":"2402.13846","title":"Large Language Models are Advanced Anonymizers","created":"2024-02-21","cited_by_count":22,"area":null},{"id":"2301.09112","title":"Differentially Private Natural Language Models: Recent Advances and Future Directions","created":"2023-01-22","cited_by_count":20,"area":null},{"id":"2306.05561","title":"Privacy- and Utility-Preserving NLP with Anonymized Data: A case study of Pseudonymization","created":"2023-06-08","cited_by_count":18,"area":null},{"id":"2104.11838","title":"On a Utilitarian Approach to Privacy Preserving Text Generation","created":"2021-04-23","cited_by_count":17,"area":null},{"id":"2306.01471","title":"Guiding Text-to-Text Privatization by Syntax","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2407.11770","title":"Robust Utility-Preserving Text Anonymization Based on Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2205.06895","title":"Bootstrapping Text Anonymization Models with Distant Supervision","created":"2022-05-13","cited_by_count":8,"area":null},{"id":"2501.09765","title":"Enhancing the De-identification of Personally Identifiable Information in Educational Data","created":"2025-01-14","cited_by_count":7,"area":null},{"id":"2310.14312","title":"Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysis","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2203.06793","title":"Can pre-trained Transformers be used in detecting complex sensitive sentences? -- A Monsanto case study","created":"2022-03-14","cited_by_count":3,"area":null},{"id":"2208.06216","title":"Is Your Model Sensitive? SPeDaC: A New Benchmark for Detecting and Classifying Sensitive Personal Data","created":"2022-08-12","cited_by_count":3,"area":null},{"id":"2406.17875","title":"Cloaked Classifiers: Pseudonymization Strategies on Sensitive Classification Tasks","created":"2024-06-25","cited_by_count":3,"area":null},{"id":"2505.12859","title":"Re-identification of De-identified Documents with Autoregressive Infilling","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2208.07127","title":"Deception for Cyber Defence: Challenges and Opportunities","created":"2022-08-15","cited_by_count":2,"area":null},{"id":"2310.03777","title":"PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2405.01097","title":"Silencing the Risk, Not the Whistle: A Semi-automated Text Sanitization Tool for Mitigating the Risk of Whistleblower Re-Identification","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2406.13947","title":"AspirinSum: an Aspect-based utility-preserved de-identification Summarization framework","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2507.11862","title":"Cross-Domain Transfer and Few-Shot Learning for Personal Identifiable Information Recognition","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2510.06383","title":"Protecting De-identified Documents from Search-based Linkage Attacks","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.09184","title":"Stronger Re-identification Attacks through Reasoning and Aggregation","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2603.08207","title":"The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniques","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2608.29624","title":"PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}