Capstone
Cybersecurity
Network Intrusion Detection System
Machine-learning anomaly detection over live network traffic
- Python
- Scapy
- XGBoost
- Kafka
- +2
₹5,499₹9,499
4.9/97 reviews
Cybersecurity · Major Project
User Identification from Mouse & Keystroke Dynamics
Behavioural biometrics that keep checking who is at the keyboard
3-4 weeks build
Overview
Continuous authentication from how someone types and moves the mouse. Key hold and flight times, and mouse speed, curvature and click patterns, are turned into features and scored against each user's profile. Models are evaluated on the public CMU keystroke benchmark and the Balabit mouse dynamics dataset, and a live demo locks a session when behaviour stops matching.
What makes it stand up
- 01Keystroke hold, flight and digraph timing features
- 02Mouse speed, acceleration, curvature and click features
- 03Per-user anomaly models plus a multi-class identifier
- 04EER, FAR and FRR reported on public benchmarks
- 05Live browser demo with a rolling trust score
Module breakdown
- 01
Collection
Browser event capture of key and mouse timings.
- 02
Features
Windowed keystroke and mouse movement statistics.
- 03
Models
One-class SVM and isolation forest per user, random forest across users.
- 04
Evaluation
EER curves on the CMU and Balabit datasets.
- 05
Live demo
Flask scoring API and React trust meter that locks the session.
After this, you will be able to
- Explain FAR, FRR and the equal error rate
- Defend continuous authentication against one-time login
- Demo the session locking when another person takes over
Technology stack
- Python
- scikit-learn
- Pandas
- Flask
- React
- Level
- Major Project
- Domain
- Cybersecurity
- Build time
- 3-4 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support