Today for AI
HOT RADAR
toolsHEAT 0.0°

AI CLUSTERED EVENT · 10/10/2026

NDS Open-Sources Rampart: Browser-Native On-Device PII Redaction Using MiniLM and Regex

1 reports archived0 independent sourcesupdated 10/10/2026, 01:52:07
Synthesis & Latest Updates

The National Design Studio (NDS) has open-sourced Rampart, a browser-native on-device system for filtering Personally Identifiable Information (PII). It employs a hybrid architecture combining deterministic regex for structured data like SSNs and lightweight MiniLM models to detect unstructured entities such as names and addresses, ensuring sensitive data is redacted before leaving the device.

LATEST/The National Design Studio (NDS) has open-sourced Rampart, a browser-native on-device system for filtering Personally Identifiable Information (PII). It employs a hybrid architecture combining deterministic regex for structured data like SSNs and lightweight MiniLM models to detect unstructured entities such as names and addresses, ensuring sensitive data is redacted before leaving the device.

HEAT TRENDHourly heat curve

43 fully observed hours
Now
0.0
Peak
9.510-11
24h change
-100%

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. Hacker News AIT2·68 pts
    • Rampart runs entirely in the browser without relying on remote servers or large binary downloads, ensuring data never leaves the device.
    • It uses a dual-layer defense: regex for high-confidence structured PII and MiniLM for semantically complex unstructured PII.
    • As an open-source tool from a government-backed studio, it aims to provide verifiable privacy infrastructure for citizens, setting an industry precedent.
NDS Open-Sources Rampart: Browser-Native On-Device PII Redaction Using MiniLM and Regex | Today for AI