{"url":"/task/de-identification","name":"De-identification","slug":"de-identification","description_markdown":"De-identification is the task of detecting privacy-related entities in text, such as person names, emails and contact data.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":174,"papers_with_code":54,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":2,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/i2b2-de-identification-dataset","name":"i2b2 De-identification Dataset","full_name":"Informatics for Integrating Biology and the Bedside (i2b2) Project — De-identification Dataset","num_papers_in_archive":4},{"url":"/dataset/dataset-privacy-preserving-gaze-data","name":"Dataset: Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experience.","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/full-body-anonymization","name":"Full-body anonymization"},{"url":"/task/privacy-preserving-deep-learning","name":"Privacy Preserving Deep Learning"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":54,"tagged_in_all":174,"items":[{"url":"/paper/ego4d-around-the-world-in-3000-hours-of","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","date":"2021-10-13","arxiv_id":"2110.07058","repositories_listed":8,"syntology":{"n":15,"n_ran":4,"n_unverified":11,"n_pointer_only":2}},{"url":"/paper/disentangling-in-latent-space-by-harnessing-a","title":"Face Identity Disentanglement via Latent Space Mapping","date":"2020-05-15","arxiv_id":"2005.07728","repositories_listed":3,"syntology":null},{"url":"/paper/synthesis-of-realistic-ecg-using-generative","title":"Synthesis of Realistic ECG using Generative Adversarial Networks","date":"2019-09-19","arxiv_id":"1909.09150","repositories_listed":3,"syntology":null},{"url":"/paper/publicly-available-clinical-bert-embeddings","title":"Publicly Available Clinical BERT Embeddings","date":"2019-04-06","arxiv_id":"1904.03323","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/de-identification-of-medical-imaging-data-a","title":"De-Identification of Medical Imaging Data: A Comprehensive Tool for Ensuring Patient Privacy","date":"2024-10-16","arxiv_id":"2410.12402","repositories_listed":2,"syntology":null},{"url":"/paper/echonet-synthetic-privacy-preserving-video","title":"EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing","date":"2024-06-02","arxiv_id":"2406.00808","repositories_listed":2,"syntology":null},{"url":"/paper/the-text-anonymization-benchmark-tab-a","title":"The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization","date":"2022-01-25","arxiv_id":"2202.00443","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/speech-pseudonymisation-assessment-using","title":"Speech Pseudonymisation Assessment Using Voice Similarity Matrices","date":"2020-08-30","arxiv_id":"2008.13144","repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-clinical-models-with-pseudo-data","title":"Enhancing Clinical Models with Pseudo Data for De-identification","date":"2025-06-15","arxiv_id":"2506.12674","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-generation-of-synthetic","title":"Zero-shot generation of synthetic neurosurgical data with large language models","date":"2025-02-13","arxiv_id":"2502.09566","repositories_listed":1,"syntology":null},{"url":"/paper/the-devil-is-in-the-prompts-de-identification","title":"The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generation","date":"2025-02-11","arxiv_id":"2502.07516","repositories_listed":1,"syntology":null},{"url":"/paper/svia-a-street-view-image-anonymization","title":"SVIA: A Street View Image Anonymization Framework for Self-Driving Applications","date":"2025-01-16","arxiv_id":"2501.09393","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-the-de-identification-of-personally","title":"Enhancing the De-identification of Personally Identifiable Information in Educational Data","date":"2025-01-14","arxiv_id":"2501.09765","repositories_listed":1,"syntology":null},{"url":"/paper/medical-manifestation-aware-de-identification","title":"Medical Manifestation-Aware De-Identification","date":"2024-12-14","arxiv_id":"2412.10804","repositories_listed":1,"syntology":null},{"url":"/paper/in-context-learning-for-preserving-patient","title":"In-Context Learning for Preserving Patient Privacy: A Framework for Synthesizing Realistic Patient Portal Messages","date":"2024-11-10","arxiv_id":"2411.06549","repositories_listed":1,"syntology":null},{"url":"/paper/low-latency-video-anonymization-for-crowd","title":"Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy vs. Performance","date":"2024-10-24","arxiv_id":"2410.18717","repositories_listed":1,"syntology":null},{"url":"/paper/deidclinic-a-multi-layered-framework-for-de","title":"DeIDClinic: A Multi-Layered Framework for De-identification of Clinical Free-text Data","date":"2024-10-02","arxiv_id":"2410.01648","repositories_listed":1,"syntology":null},{"url":"/paper/generating-synthetic-free-text-medical","title":"Generating Synthetic Free-text Medical Records with Low Re-identification Risk using Masked Language Modeling","date":"2024-09-15","arxiv_id":"2409.09831","repositories_listed":1,"syntology":null},{"url":"/paper/generation-and-de-identification-of-indian","title":"Generation and De-Identification of Indian Clinical Discharge Summaries using LLMs","date":"2024-07-08","arxiv_id":"2407.05887","repositories_listed":1,"syntology":null},{"url":"/paper/automated-privacy-preserving-techniques-via","title":"Automated Privacy-Preserving Techniques via Meta-Learning","date":"2024-06-24","arxiv_id":"2406.16456","repositories_listed":1,"syntology":null},{"url":"/paper/chexpert-plus-hundreds-of-thousands-of","title":"CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats","date":"2024-05-29","arxiv_id":"2405.19538","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/computational-job-market-analysis-with","title":"Computational Job Market Analysis with Natural Language Processing","date":"2024-04-29","arxiv_id":"2404.18977","repositories_listed":1,"syntology":null},{"url":"/paper/rid-twin-an-end-to-end-pipeline-for-automatic","title":"RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos","date":"2024-03-15","arxiv_id":"2403.10058","repositories_listed":1,"syntology":null},{"url":"/paper/a-privacy-preserving-unsupervised-speaker","title":"A Privacy-Preserving Unsupervised Speaker Disentanglement Method for Depression Detection from Speech","date":"2024-02-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-reliable-generation-of-ehr-time","title":"Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Models","date":"2023-10-23","arxiv_id":"2310.15290","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":11}},{"url":"/paper/fast-refacing-of-mr-images-with-a-generative","title":"Fast refacing of MR images with a generative neural network lowers re-identification risk and preserves volumetric consistency","date":"2023-05-26","arxiv_id":"2305.16922","repositories_listed":1,"syntology":null},{"url":"/paper/escoxlm-r-multilingual-taxonomy-driven-pre","title":"ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain","date":"2023-05-20","arxiv_id":"2305.12092","repositories_listed":1,"syntology":null},{"url":"/paper/in-the-name-of-fairness-assessing-the-bias-in","title":"In the Name of Fairness: Assessing the Bias in Clinical Record De-identification","date":"2023-05-18","arxiv_id":"2305.11348","repositories_listed":1,"syntology":null},{"url":"/paper/k-salsa-k-anonymous-synthetic-averaging-of","title":"k-SALSA: k-anonymous synthetic averaging of retinal images via local style alignment","date":"2023-03-20","arxiv_id":"2303.10824","repositories_listed":1,"syntology":null},{"url":"/paper/deid-gpt-zero-shot-medical-text-de","title":"DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4","date":"2023-03-20","arxiv_id":"2303.11032","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}