Skip to content

Web-Based Behavioral Keystroke Authentication.

Notifications You must be signed in to change notification settings

prakadesh/CogniKey

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CogniKey: Behavioral Biometrics Authentication

Welcome to CogniKey, a pioneering web-based authentication system that transforms security through the fusion of cognitive and behavioral biometrics. In this digital age where identities are paramount, CogniKey takes the lead by harnessing the nuances of individual behaviors to create a strong authentication foundation.

INTRODUCTION

Due to rapid digitization of the industry, data has become one of the most valuable and critical assets of enterprises. Data leakage is a serious threat for companies, which can cause massive financial and reputational loses. This is why, increasing security in order to prevent data loss is one of the most pressing objectives for enterprises today. There are several ways in which data can be leaked from inside a company. It is often said that end users are the weakest link in a security chain. After all, even if all data is encrypted, if an attacker manages to compromise devices belonging to internal employees, they could get access inside the enterprise. There could also be cases where an internal employee intentionally leaks data for various reasons like sabotaging or revenge. Most commonly, users are asked to log in using either something they know, for example user names and passwords, something they have, For example tokens or smart cards or something they are, for example biometrics like fingerprint sensors or face detection. In order to strengthen security even more, combinations of these methods can be used. However, once the authenticity of the users is confirmed by any of these methods, under the process called authentication, they are granted access to the systems. If the actual user changes while the log in is still active, for example, another person physically or remotely takes control of the computer, these authentication methods don’t provide a straightforward way to sense the change. This problem raises the need of an authentication system that can perform continuous authentication of the user. Such systems should be able to learn the behavior of the users based on their interaction with a system, for example their typing or mouse movement patterns, and be able to differentiate legitimate users from intruders. Furthermore, as productivity in an enterprise very important, these systems should be transparent and non-intrusive with the user’s work and should not require extra hardware added to the systems. With the latest developments in the machine learning field, the possibility of developing such systems that would provide good performance is possible. Called, behavioral biometrics, these authentication technologies promise to offer continuous authentication of users based on their computer usage patterns. The system should be transparent in order to not affect productivity while ensuring the privacy of the user.

Objective of the Work

Objectives of the project is to make a system that will • Authenticate users on the basis of their keystroke dynamics. • With increasing security concerns in traditional approaches like username password keystroke dynamics will be a key changer in the field of online security and human identification. • Make online communication more secure as at any time to use the system we require the person not his/her username and password.

System Architecture

The following figure depicts the system architecture for Keystroke Dynamic for the Online system. It is a Client-Server connection. A user or client needs to type his/her username and password to access the system. During this process on the client-side, the system will capture the pattern of the user’s typing. Then, this pattern will be sent to the Keystroke Dynamic Server to be verified using the matching algorithm and verify. Once the result is matched (positive), the user is granted to enter the system. image

WORK-FLOW

The given flowchart shows the process of the keystroke dynamic prototype system. This involves two major parts primarily a user need to register into the dynamic keystroke system then. They have to enter their details such as name, email, contact number, username, and password. Once they enter they have to enter the given phrase 10 times to capture their keystroke dynamics and data is stored in the used for future verification process.

image

USAGE

we can launch the website using the python file server.py

Screenshots

image image image image image

About

Web-Based Behavioral Keystroke Authentication.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published