A modern ML-powered biometric authentication system that identifies users based on their unique typing patterns. Built with Streamlit, scikit-learn, and Material Design 3.

Passwordless, client-side authentication

An intelligent Android keyboard that leverages unique typing patterns for user identification, enabling secure authentication.

This project explores user authentication on mobile devices through typing patterns, leveraging touch and motion data. Using machine learning models, particularly LSTM, the research demonstrates superior user classification accuracy compared to traditional RNN models, enhancing security against ATO attacks.