Hershey, Pennsylvania
New York, New YorkBeijing, China
A Wrapper-Based Classification Approach for Personal Identification through Keystroke Dynamics Using Soft Computing Techniques

A Wrapper-Based Classification Approach for Personal Identification through Keystroke Dynamics Using Soft Computing Techniques

Shanmugapriya D. (Avinashilingam Institute for Home Science and Higher Education for Women, India) and Padmavathi Ganapathi (Avinashlingam Institute for Home Science and Higher Education for Women, India)
Copyright: © 2017 |Pages: 24
DOI: 10.4018/978-1-5225-0808-3.ch013
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The password is the most widely used identity verification method in computer security domain. However, due to its simplicity, it is vulnerable to imposters. A way to strengthen the password is to combine Biometric technology with password. Keystroke dynamics is one of the behavioural biometric approaches which is cheaper and does not require any sophisticated hardware other than the keyboard. The chapter uses a new feature called Virtual Key Force along with the commonly extracted timing features. Features are normalized using Z-Score method. For feature subset selection, Particle Swarm Optimization wrapped with Extreme Learning Machine is proposed. Classification is done with wrapper based PSO-ELM approach. The proposed methodology is tested with publically available benchmark dataset and real time dataset. The proposed method yields the average accuracy of 97.92% and takes less training and testing time when compared with the traditional Back Propagation Neural Network.
Chapter Preview
Top

Introduction

The confidential information can be secured from unauthorized users by providing authentication. User authentication is defined as the process of verifying the identity claimed by an individual. User Authentication is normally classified into three categories namely, Knowledge based Authentication, Object based Authentication, and Biometric based Authentication (Lawrence O’Gorman, 2003) which is shown in Figure 1.

Figure 1.

Authentication types

978-1-5225-0808-3.ch013.f01

Knowledge based Authentication is based on “something the user knows”. User name and passwords come under this category. However, passwords are vulnerable to password hackers because the users sometimes can't remember the strong passwords and they write them down. Something the user has or possesses is called Object based authentication. Tokens or Personal Identification Numbers (PINs) are the widely used examples of this type of authentication. Tokens are easy to misplace or damage and PINs are vulnerable to shoulder surfing and systematic trial-and-error attacks (Seong-seob Hwang, Cho and Park, 2009). Biometric based authentication provides a very reliable method of authenticating a user and is divided into physiological and behavioral types (Francesco and Picardi, 2002). Physiological biometrics refer to what the person is or they measure physical parameters of certain parts of the body and Behavioral biometrics shows how the person is using the body for authentication. Figure 2. shows an example of different types of biometrics.

Figure 2.

Different types of biometrics

978-1-5225-0808-3.ch013.f02

Each type of biometrics has its own advantages and limitations. Physiological biometrics are considered to be extremely robust and hence more secure. However, these types of biometrics are not portable and cannot be used for web based applications. Behavioral biometrics such as voice, gait etc., face the problem of high implementation cost as they require special hardware or sensors for capturing the template. An analysis of different types of biometrics is given in the following Table 1.

Table 1.
Analysis of different types of biometrics
Physiological BiometricsBehavioral Biometrics
What the person is or measure physical parameters of a certain part of the bodyWhat a person does or how the person uses the body
Examples: Fingerprint, Iris, Face Recognition, etc.,Examples: Voice, Handwriting, walking gait, Typing rhythm or Keystroke Dynamics
Limitations:
• Can be spoofed
• Difficulties in implementing
• Expensive
• Requires special Hardware
• More Intrusive		Limitations:
• Voice Recognition, the most promising technology but it is difficult to distinguish a live user from a recorded one
• Handwriting, gait requires a special device, which can be cost prohibitive and signatures can be forged

Complete Chapter List

Search this Book:
Reset