Dark Mode

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

IEEE-VIT/priv-guard

Repository files navigation

PrivGuard - AI Personal Privacy Risk Analyzer

PrivGuard is a mobile-first, privacy-focused app that helps users detect oversharing risks in their digital content. Whether it's social media posts, images, or bios, PrivGuard uses custom on-device AI to analyze content and flag potential privacy threats, ensuring your data never leaves your phone or trusted backend.


Real-World Use Case

Over 90% of digital threats begin with publicly available data.

PrivGuard educates and protects users by identifying:

  • Posts that reveal personal details
  • Real-time travel or location risks
  • Information linked to password recovery
  • IDs, documents, tickets captured in photos

Core Features

Upload & Local Scan

  • Capture or upload media/text posts
  • Securly save to local storage
  • Long-press to run on-device scan

AI Privacy Analysis

  • Text classifier: NER-based risk labeling with DistilBERT
  • Risk Score: 0-100 with Low, Medium, High tag
  • Smart Tips: Context-aware advice (e.g., mask phone numbers, generalise location)
  • Image Scanning: Object detection to extract and detect any risky details from image post (AVAILABLE IN FUTURE VERSIONS)

Social Profile Risk Scanner (AVAILABLE IN FUTURE VERSIONS)

  • Input Instagram/Twitter handle + email
  • Uses Instaloader / snscrape to fetch data
  • NLP analysis of bio, captions, hashtags
  • Auto-rescan every 30 days with push alerts

App Architecture/Tech Stack

Phase Feature Stack
1 Upload UI + Gallery Flutter, path_provider, image_picker
2 AI Risk Detection DistilBERT, tflite_flutter,HuggingFace Transformers
3 Security flutter_secure_storage, encrypt

Custom AI Module

  • Fine-tuned DistilBERT to detect Personally Identifiable Information present in given text
  • Detects terms like:
    1. Names
    2. Dates
    3. Locations
    4. Phone numbers
    5. Credit card details
    6. Date of birth and other personal details

App Screens (UI Flow)

  1. Gallery Screen

    • Grid view of all uploaded content
    • Scan option on long-press
  2. Scan Result Screen

    • Risk tag + reason: "Passport detected" or "Location inferred"
    • Actionable suggestions
  3. Social Media Scanner

    • Input handle + email
    • View/email detailed report
    • Enable auto-scan mode

Data Privacy & Ethics

  • All analysis is performed locally
  • No 3rd-party cloud APIs (e.g., Google Vision, Gemini)
  • All posts, media files stored securly in local storage

Colab Notebook for AI Model

Google Colab Notebook


Getting Started

To Run the application locally-

  1. This repo uses Git LFS to store large model files. Before cloning, install Git LFS
    git lfs install.
  2. Clone the repository
    git clone https://github.com/Shaurya-Saini/Priv_Guard.git
    cd Priv_Guard
    git lfs pull
  3. Create project
    flutter create .
  4. Run the application using an emulator from Android studio
    flutter run

A few resources to get you started if this is your first Flutter project:

For help getting started with Flutter development, view the online documentation, which offers tutorials, samples, guidance on mobile development, and a full API reference.

About

PrivGuard is a mobile-first app designed to help users analyze and protect their digital privacy. It allows users to scan photos, videos, and social media content to detect potential oversharing risks using AI -- while ensuring user data never leaves their device or trusted backend.

Topics

Resources

Readme

License

MIT license

Contributing

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

Contributors