Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/t-mohamed-shafeek/piipit
piipit is a Hybrid PII Detection and Management Full-Stack Web Application built using my novel approach of multi-layered detection mechanism for more Accurate Detection of Personally Identifiable Information (PII) and Reduced Latency.
https://github.com/t-mohamed-shafeek/piipit
css detection flask full-stack-web-development fullstack-development gemini html java llama3 llm management masking pattern-matching python react redaction sqlalchemy ui
Last synced: about 2 months ago
JSON representation
piipit is a Hybrid PII Detection and Management Full-Stack Web Application built using my novel approach of multi-layered detection mechanism for more Accurate Detection of Personally Identifiable Information (PII) and Reduced Latency.
- Host: GitHub
- URL: https://github.com/t-mohamed-shafeek/piipit
- Owner: T-Mohamed-Shafeek
- License: bsd-3-clause
- Created: 2024-10-10T19:39:20.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2024-12-04T16:00:25.000Z (about 2 months ago)
- Last Synced: 2024-12-04T17:18:46.162Z (about 2 months ago)
- Topics: css, detection, flask, full-stack-web-development, fullstack-development, gemini, html, java, llama3, llm, management, masking, pattern-matching, python, react, redaction, sqlalchemy, ui
- Homepage:
- Size: 2.91 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# piipit - A Hybrid PII Detection and Management Application
## Project Overview
The Hybrid PII Detection and Management application is designed to identify and protect Personally Identifiable Information (PII) embedded in various data and document formats, including images. This application focuses specifically on government-issued documents such as Aadhaar, PAN, Driving License, Passport, MHA ID, and Credit Cards.
## Key Features
- **Multi-Format PII Detection:** Supports PDF, DOCX, TXT, CSV, and image formats.
- **Government Document Focus:** Specializes in detecting PII in Indian government-issued documents.
- **Alerting System:** Notifies users and data processors about the presence of PII.
- **Pattern Matching and Context-Based Detection:** Uses regex for strong/structured PII and NLP for weak/unstructured PII.
- **Redaction and Masking:** Provides tools to redact or mask detected PII.
- **Secure Data Management:** Ensures secure user authentication and data handling.
## Current Status
The project is currently 90% complete, with ongoing development in UI and feature enhancements. Testing, bug fixing, and validation processes are in progress.
## Future Plans
- Finalize the remaining features and UI improvements.
- Conduct thorough testing and validation.
- Prepare for potential open-source release in the future.
## Technologies Used
- **Frontend:** React.js, Chakra UI
- **Backend:** Python, Flask Framework
- **AI/ML:** LangChain, Groq API, Llama3.1 for NLP tasks
- **File Processing:** PyPDF2, python-docx, Pillow, easyocr
## Contact
For inquiries or collaboration opportunities, please reach out to me at [email protected].
## License
This project is currently not open-source. Please check back later for updates on licensing and potential open-source release.