Biometric-Authentication-Using-Mouse-Dynamics Mini Project

Physics-constrained offline RL pipeline for synthetic human mouse telemetry in behavioral-biometrics and continuous-authentication research (MuJoCo, d3rlpy, Balabit).

An open sourced approach to One-Shot Learning for Mouse Dynamics recognition in PyTorch. This includes tools for data preprocessing, training both classification and embedding models, and evaluating model performance on a Minecraft dataset.

Python project that uses machine learning to identify users based on their mouse movement patterns. It analyzes behavioral datasets and applies supervised learning techniques for behavior-based biometric authentication.

A survey of the behavioral layer of bot detection and the limits of synthetic human input: what detectors measure, how mouse and keystroke input is synthesized, and why the popular generators are the easiest to catch.

Continuous Authentication System using Behavioural Biometric Recognition

SecureAuth Enterprise is a behavioral biometric authentication platform that enhances cybersecurity by analyzing keystroke dynamics, mouse behavior, facial recognition, and WebAuthn biometrics for continuous user verification.

Real-time AI stress tracker using mouse & keystroke dynamics. Privacy-first, local-only, and 100% offline.

Mouse Dynamics-Based Intrusion Detection using Recurrence Plots and Vision Transformers

A real-time continuous authentication system using face recognition (FaceNet), keystroke dynamics (LSTM Autoencoder), and mouse dynamics (GRU Autoencoder) with a Chrome extension, FastAPI backend, and React admin portal.