Tag
Liquid AI's LFM2.5-Encoders can identify and strip 40 types of PII across 16 languages in one pass, designed for secure AI data processing within private pipelines.
OpenMed privacy-filter v2 using nemotron and MLX 8-bit achieves 755 tokens per second on a Mac, redacting 1,152 PII identifiers across 22 categories from a 13,000-token clinical file without data leaving the machine.
Engineers Edward Coristine and Tai Groot released Rampart, an open-source AI privacy model for on-device PII redaction that runs entirely in the browser, developed by the National Design Studio.
RedactionBench is a manually annotated benchmark for evaluating contextual PII redaction in large language models, introducing the R-Score metric and showing that contextual redaction remains an unsolved problem.
OpenMed 1.5.5 ships with batch PII redaction on-device in 9 languages, open-source under Apache 2.0, having surpassed 6 million PyPI downloads in under a year.
Describes an agent stack design where a frontier LLM orchestrates fine-tuned small language models for PII redaction, ensuring privacy by keeping raw text local.