Mini-project
Cybersecurity & Digital Trust
Scam SMS and email detector
Detect phishing and UPI scam messages in English and Hindi, and explain what makes each suspicious.
The brief
Fake KYC, lottery and UPI refund messages trick people every day. Build a detector for scam SMS and emails that works in English and Hindi, and explains in plain words which signs made a message suspicious. Good looks like: accuracy on English and Hindi test sets, explanations per message, and few false alarms on genuine bank messages.
What you will build
- Combine public spam data with Indian scam examples
- Train a classifier and a multilingual model
- Test on English and Hindi messages
- Explain the suspicious signs per message
- Measure false alarms on genuine bank messages
Free, open data to build it with
- SMS Spam Collection ↗ UCI Machine Learning Repository
- Phishing email dataset ↗ Kaggle
Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.