https://github.com/davidpomerenke/securedact

Redact sensitive information from PDFs before liberating them!
https://github.com/davidpomerenke/securedact

ai anonymization pdf redaction

Last synced: 7 months ago
JSON representation

Redact sensitive information from PDFs before liberating them!

• Host: GitHub
• URL: https://github.com/davidpomerenke/securedact
• Owner: davidpomerenke
• Created: 2024-11-06T11:53:46.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2025-01-30T14:09:29.000Z (8 months ago)
• Last Synced: 2025-01-30T15:22:59.952Z (8 months ago)
• Topics: ai, anonymization, pdf, redaction
• Language: TypeScript
• Homepage: https://freedomizer.bmz.dev
• Size: 5.16 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# ⬛️ SecuRedact

A tool for redacting sensitive information from PDF documents using AI assistance.

> ⚠️ **DISCLAIMER**: This software is currently in development and not yet ready for production use. Use at your own risk and always verify redactions manually.

Everything runs completely locally in your browser.

Older devices can optionally connect to a server to speed things up.

## Features

- [x] [display and annotate PDFs](https://github.com/agentcooper/react-pdf-highlighter)

- [x] [safely redact the PDF based on the annotations](https://github.com/ArtifexSoftware/mupdf.js)

- [x] [use AI to automatically detect personal information](https://github.com/huggingface/transformers.js)

  - [x] [based on named entity recognition](https://huggingface.co/Xenova/bert-base-multilingual-cased-ner-hrl)

  - [ ] [based on chat models](https://huggingface.co/onnx-community/Qwen2.5-1.5B-Instruct;https://huggingface.co/onnx-community/Llama-3.2-1B-Instruct)

  - [ ] [optionally connect to large language models](https://github.com/vllm-project/vllm)

- [ ] [supports scanned PDFs](https://github.com/naptha/tesseract.js/)

- [ ] [converts Word documents to PDF](https://github.com/georgestagg/pandoc-wasm)

## License

MIT License (c) BMZ / David Pomerenke

The frontend is based on an example from [react-pdf-highlighter](https://github.com/agentcooper/react-pdf-highlighter/), MIT License.