pseudonymization

A curated list of resources related to privacy engineering

Privacy transformation engine for structured datasets — pseudonymization and risk-assessed anonymization for CSV files, driven by a declarative YAML policy.

A privacy and security engineering toolkit: Discover, understand, pseudonymize, anonymize, encrypt and securely share sensitive and personal data: Privacy and security as code.

한국어 PII 검출 + 가명화 Python 라이브러리

The Privacy Firewall for LLMs

A run anywhere database anonymizer

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

Privacy middleware for LLM & RAG pipelines - consistent pseudonymization, encrypted vault, SSE streaming rehydration.

Private Input Masked Output - PIMO is a tool for data masking (anonymization, pseudonymization, ...).

Private Prompts Prototype Documentation

A buddy check for your prompts — before they reach an LLM. On-device, reversible anonymization that catches the PII you didn't mean to send.

Overview of tools to de-identify, synthesize and work safely with (sensitive) data

A local-LLM privacy layer for anything you paste into a cloud model — detect, tokenize, restore. Zero deps, reversible, strong on Chinese.

High-speed PII masking as a Polars plugin, powered by Rust

A REST service to pseudonymize and anonymize FHIR® resources.

serverless ☁️ 🚀 , pseudonymizing proxy between Worklytics and your workplace 💼 SaaS data sources' APIs. Data Loss Prevention (DLP) 🛡️🔒 and compliance layer deployable to AWS Lambda or GCP Cloud Functions.

Reversible PII masking for LLM agents: piighost replaces personal data with placeholders before the model sees it, then restores the real values in replies and tool calls. LangChain, Pydantic AI, LlamaIndex and Claude Code integrations, plus an OpenAI/Anthropic-compatible proxy.

Etalab's Lab IA Pseudonymization Demo source code

Encrypt PII, not meaning. Locally.

Redactify is an efficient data redaction tool that secures sensitive text using advanced NLP and rule-based methods. It combines transformer-based NER, regex, and Presidio analysis to detect and mask personal information through full redaction or partial masking—ensuring compliance while preserving data utility.