An intelligent, real-time cyber safety system designed to detect, analyze, and prevent digital fraud across SMS, URLs, and online communication platforms.
With the rapid rise of phishing attacks, UPI scams, and fraudulent messages, this project aims to build an AI-driven security layer that protects users from cyber threats in real time. The system leverages Natural Language Processing (NLP), machine learning, and external threat intelligence APIs to identify suspicious and malicious activity.
-
🔍 Smart Message Scanner
Detects spam, phishing, and scam messages using NLP models. -
🌐 URL Phishing Detection
Identifies malicious links using feature-based ML models and external APIs. -
🤖 AI-Based Fraud Detection
Classifies inputs as Safe, Suspicious, or Fraud. -
⚠️ Real-Time Alerts
Notifies users instantly about potential threats and suggests actions. -
📊 User Risk Dashboard
Tracks fraud history, risk score, and insights. -
📱 Mobile App Integration
Enables real-time scanning of SMS and user interactions.
- NLP Models: TF-IDF, Logistic Regression, DistilBERT (planned)
- Phishing Detection: Feature-based ML models
- Anomaly Detection: Isolation Forest
- Text Processing: Regex, preprocessing pipelines
- Frontend: Flutter
- Backend: FastAPI (Python)
- Database: MongoDB / Firebase
- ML/AI: Scikit-learn, Transformers (Hugging Face)
- APIs: Google Safe Browsing, VirusTotal, Firebase FCM
ml-models/→ Data processing, feature engineering, model trainingbackend/→ FastAPI APIs and model integrationmobile-app/→ Flutter-based mobile applicationdocs/→ Documentation
- SMS spam/fraud detection
- URL phishing detection
- Basic alert system
- Backend API integration
This system aims to enhance digital safety by proactively detecting fraud and empowering users with real-time insights, contributing to a safer online ecosystem.