Skip to content

jongyunhur/WatchCall

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

WatchCall

AI+SECURITY_._.Aich.pdf

Real-time Voice Phishing Detection System

Submitted to the 2023 KISA AI+Security Idea Competition. Used FSS and AI Hub datasets for academic research.

Overview

Voice phishing targeting people in their 20s now accounts for 30% of total cases, but existing prevention methods only work after the damage is done. WatchCall detects suspicious patterns in real-time during phone calls to prevent fraud.

Features

  • Real-time analysis: Detects suspicious patterns during calls
  • Text + Voice analysis: Analyzes both conversation content and voice tone
  • Call summary: Summarizes long conversations
  • Instant alerts: Warns immediately when risks are detected

How It Works

Text Analysis

Searches for phishing keywords like "urgent transfer", "legal action", "account suspension". Uses context analysis instead of simple keyword matching.

Voice Analysis

AI voices sound different from real human voices:

  • Background noise (AI voices are usually clean)
  • Voice intensity and frequency patterns
  • Emotional changes (AI voices are unnatural)

Deepvoice Detection

Since scammers now use AI-generated voices, we added a model to distinguish them. Uses voice-to-text confidence scores and MFCC features for detection.

Data & Models

Datasets

  • Financial Supervisory Service: Real voice phishing cases and transcripts
  • AI Hub: Customer service call data

Model Architecture

  1. NER-based text analysis
  2. MFCC voice feature extraction
  3. Deepvoice detection model
  4. Ensemble for final prediction

Sends alerts when both text and voice models flag the call as suspicious.

Output

After each call:

  • Call summary (who and what)
  • Risk level (red/yellow/green alerts)
  • Full conversation text with highlighted suspicious parts

Future Work

  • Real-time fraud pattern updates via police database integration
  • SMS phishing detection
  • Bank FDS system integration
  • Guardian alerts for elderly users

Contact

Feel free to reach out if you have questions.

About

Model Training for Real-time Speech Recognition and AI-driven Analysis to Prevent Financial Fraud and Voice Phishing

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors