PII Detection

PII: Personally Identifiable Information

Ask about this topic

Overview

PII detection locates details such as names, addresses, health information, and account identifiers so they can be protected before data is shared or processed. Systems range from rules and pattern matching to transformer-based entity taggers and prompted large language models, with OCR and vision methods used for documents and interfaces. They are evaluated on settings including clinical notes, multilingual text, long conversations, and synthetic benchmarks such as PIIBench, where performance depends on domain and identifier type. A central challenge is balancing missed disclosures against unnecessary redaction: contextual ambiguity, distribution shifts, and aggregate scores can hide failures that matter for privacy and data utility.

Latest papers

CardsList

39 papers7 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. Hardening x402: PII-Safe Agentic Payments via Pre-Execution Metadata Filtering

    Apr 13, 2026Vladimir StantchevAI Agent SecuritySafety Filtering

    SRH University Heidelberg, Germany · PRESIDIO Group, Sofia, Bulgaria

  2. Identification and Anonymization of Named Entities in Unstructured Information Sources for Use in Social Engineering Detection

    Apr 10, 2026Carlos Jimeno Miguel, Raul Orduna, Francesco ZolaPII DetectionNamed Entity Recognition

    Public University of Navarre Pamplona, Spain · Vicomtech San Sebasti´an, Spain

  3. BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines

    Apr 7, 2026Bo Ma, Jinsong Wu, Weiqi YanData LeakagePrivacy-Preserving Language Models

    Auckland University of Technology Auckland, New Zealand · Guilin University of Electronic Technology Guilin, China

  4. Towards Context-Aware Image Anonymization with Multi-Agent Reasoning

    Mar 29, 2026Robert Aufschläger, Jakob Folz, Gautam Savaliya +3PII Detection

    Deggendorf Institute of Technology, Deggendorf, Germany

  5. WebPII: Benchmarking Visual PII Detection for Computer-Use Agents

    Mar 18, 2026Nathan ZhaoPII DetectionPrivacy-Preserving ML

    Stanford University

  6. MultiGraSCCo: A Multilingual Anonymization Benchmark with Annotations of Personal Identifiers

    Mar 9, 2026Ibrahim Baroud, Christoph Otto, Vera Czehmann +4Synthetic Benchmark GenerationClinical NLP

    1German Research Center for Articial Intelligence (DFKI) · 3Technische Universität Berlin · University of Potsdam +3

  7. Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs

    Mar 5, 2026Patrick Ahrend, Tobias Eder, Xiyang Yang +2Privacy Leakage in Language ModelsPrivacy-Preserving Language Models

    Technical University of Munich, Germany

  8. Personal Information Parroting in Language Models

    Feb 24, 2026Nishant Subramani, Kshitish Ghate, Mona DiabMemorization in Language ModelsPrivacy Leakage in Language Models

    ♠Carnegie Mellon University - Language Technologies Institute · University of Washington

  9. Utility-Preserving De-Identification for Math Tutoring: Investigating Numeric Ambiguity in the MathEd-PII Benchmark Dataset

    Feb 18, 2026Zhuqian Zhou, Kirk Vanacore, Bakhtawar Ahtisham +7PII DetectionPrivacy-Preserving ML

    Cornell University · Fresh Cognate · UPchieve +1