Skip to content
Work data is processed in your browser, not stored on our servers.
tools
PII Detector and Text Masking Tool

PII Detector and Text Masking Tool

Mask structured patterns such as email and phone numbers, with optional BERT NER detection for candidate names, organizations, and locations.

Source text
Mask email addresses, phone numbers, Korean resident IDs, cards, and IP addresses immediately with rules. AI can additionally detect names and organizations.
Masked result

Hello, my name is Alex Kim and I work at Example Corp. My phone number is [PHONE] and my email is [EMAIL]. The server IP is [IP] and the card number is [CREDIT CARD].

EMAIL 1CREDIT CARD 1PHONE 1IP 1

Your text is not sent to a server. Regular expressions run immediately, while names and organizations are detected by an AI model stored in this browser.

Key features

  • Immediately masks email, Korean resident ID, card, phone, and IPv4 patterns
  • Optionally uses BERT NER to find candidate names, organizations, and locations
  • Reports the number of matches by detected type
  • Replaces matched spans with type labels and provides copyable output

How to use

  1. Enter or paste the text you want to redact.
  2. Choose whether to use AI entity detection and run masking.
  3. Review misses and false positives before copying the result.

Examples

  • First-pass redaction before sharing

    Mask common contact and identifier formats, then inspect the text for anything remaining.

  • Find name and organization candidates

    Enable AI detection to add possible names and organizations, then review the masked output.

Privacy

Text is processed in the browser with regular expressions and, when selected, the NER model. With your consent, model files may be downloaded from Hugging Face and cached in browser storage, while your input is not sent to the model provider.

Requirements

Pattern masking works without a model. Name and organization detection needs about 181 MB of model files and cannot guarantee detection of every sensitive item, so manual review is essential.

Common questions

Which data is masked without the AI model?
Regular expressions detect common email, phone, resident-registration-number, payment-card-number, and IPv4 formats. Name and organization candidates use a separate AI model.
Does the result guarantee that all personal data is removed?
No. Unusual formats and contextual identifiers can be missed, and AI detection can have false positives or omissions. Review the output against the source.