Keystroke Dynamics Authentication with Project Management System

IJSRD - International Journal for Scientific Research & Development| Vol. 3, Issue 10, 2015 | ISSN (online): 2321-0613
All rights reserved by www.ijsrd.com 1032
Keystroke Dynamics Authentication with Project Management System
Abhijeet Patait1 Kirti Chandratre2 Gaurav Kamlaskar3 Vikas Thorat4
1,2,3,4
Department of Computer Engineering
1,2,3,4
R. H. Sapat College of Engineering, Management Studies & Research, Nashik, Maharashtra, India
Abstract— Generally user authentication is done using
username and password that is called as login process. This
login process is not more secure because, however a login
session is still unprotected to impersonator when the user
leaves his computer without logging off. Keystroke
dynamics methods can be made useful to verify a user by
extracting some typing features then, after the authentication
process has successfully ended. From the last decade several
studies proposed the use of keystroke dynamics as a
behavioral biometric tool to verify users. We propose a new
method, for representing the keystroke patterns by joining
similar pairs of consecutive keystrokes. The above proposed
method is used to consider clustering the di-graphs which
are based on their temporal features. In this project,
authentication system is provide to project management
system that make more Secure management system without
acknowledging unauthorized user. The Project Management
System addresses the management of software projects. It
provides the framework for organizing and managing
resources in such a way that these resources deliver all the
work required to complete a software project within defined
scope, time and cost constraints. The system applies only to
the management of software projects and is a tool that
facilitates decision making.
Key words: Keystroke Dynamics, Temporal Features,
Clustering Digraph, Project Management System
I. INTRODUCTION
Currently most of the system use basic security technique or
many hardware or network devices to secure his personal
computer and industrial computer. Basically now use
technology for user authentication is username password
and extends one step toward use biometric hardware system.
But such technology is not user friendly and flexible in
some cases. This biometric system make work more
complicated, lengthily and more costly. There also exist
another user behaviour authentication system this system
uses image processing technology, but there also create
some limitation because of camera.
In this paper we introduce Keystroke Dynamics
Authentication with Project Management System it uses
keystroke dynamics technology for user authentication
without using any camera and biometric hardware. This
system uses simple computer keyboard, therefor it is easy to
maintain number of systems or personal computer security.
Keystroke Dynamics Authentication system provides
security to project management system for securing the
project information and data or file which are share between
PMS employees. We are providing security in three steps
first step is examine user typing behavior, second step is one
time password (OTP) it is second verification step and the
third step is image verification step in this step select
security point on image. Therefore strength of security will
be increased.
This paper will focus on past research done on the
field of keyboard dynamics authentication. Then, the
reasoning behind the final method and a de-tailed
explanation of the final method are stated. This is followed
by test results, how efficiently the algorithm works and in
periodic time for better results as well as how we used to
test it and possible future improvements.
Fig. 1: Architecture of Keystroke Dynamics Authentication
with Project Management System”
II. MOTIVATION
Nowadays web security is most important for many
organizations, because of hacking. Most of the hacking
activity is performed for extracting some valuable
information without permission or in unauthorized way.
Traditionally we secure our valuable information
by using username and password technique, but it is not
sufficient for provide security to distributed network
environment. Therefore we introduced keystroke Dynamics
Authentication System, this system use machine learning
approach for network security. This system learns the user
typing behavior to secure user network environment.
Additionally it also provides second and third step
verification for improving the security. In this paper
proposed system is used to provide security for project
management system which is handles huge size industrial
project. The PMS system perform main role in managing the
project efficiently and reliably without requirement of any
message passing system or communication system.
III. LITERATURE SURVEY
A. Previous Research on Keystroke Dynamics
Authentication:
The effective studies done on this topic have some
resemblance. The consensus on feature selection is that key-
down to key-down produces the best results. Key-down to
key-down is the time that revealed from the user fully de-
pressing a key on the keyboard to the time the user fully
depresses the next key on the keyboard. For each key press
combination, that time is calculated and used as the
prevalent feature[1].

(IJSRD/Vol. 3/Issue 10/2015/236)
Other researchers are also uses key-press durations
as a feature. Key-press duration is the time the key is fully
depressed until the key is released. This feature, while
useful, does not perform as well as a lone feature, in
comparison to key-down to key-down time does. However,
if these features are used in combination, the results were
improved.
Tyler Highlander, Dale Bassett, Derek Boone
proposed ” Utilization of Keyboard Dynamics for Unique
Identification of Human Users [2]” In this paper they
intricate many computer security schemes have been
developed over this time period; however, none of these are
designed yet. A username and password combination is one
of the most popular approaches for securing a computer
system, but this system is unprotected because passwords
can be stolen or cracked. However, research suggests that it
is possible to identify a user based on their typing style by
using pattern recognition, neural networks, and other
techniques. This paper mainly focuses on using the
keyboard dynamics method of the user’s password to add an
extra layer of security to the log-in process.
Tomer Shimshon, Robert Moskovitch, Lior
Rokach, Yaval Elovici proposed “Clustering Di-Graphs for
Continuously Verifying Users according to their Typing
Patterns [1]” In that they have explain a new method, for
compactly representing the keystroke patterns by joining
similar pairs of consecutive keystrokes. The proposed
method considers clustering di-graphs based on their
temporal features. The proposed method was performed on
10 genuine users and 15 impostors. The inspiring results
suggest that the proposed method detection performance is
better than that of existing methods. Specifically we reach a
False Acceptance Rate (FAR) of 0.41% and a False
Rejection Rate (FRR) of 0.63%.
E. Yu, S. Cho proposed “Keystroke dynamics
identity verification - its problems and practical solutions
[3]”. In this paper they define Computers &Security;
Password is the most widely used identity verification
method in computer security system. However, because of
its simplicity, it is unguarded to imposter attacks. Use of
keystroke dynamics can result in a more secure verification
system. Recently, Cho et al. (J Organ Comput Electron
Commerce 10 (2000) 295) proposed auto associative neural
network approach, which used only the user's typing
patterns, yet reporting a low error rate: 1.0% false rejection
rate (FRR) and 0% false acceptance rate (FAR). However,
the previous research had some limitations: (1) it took too
long to train the model; (2) data were preprocessed by a
human; and (3) a large data set was required. In this article,
we propose the alternative solutions for these limitations
with an SVM novelty detector, GA–SVM wrapper feature
subset selection, and an ensemble creation based on feature
selection, respectively. Experimental results show that the
proposed methods are encouraging, and that the keystroke
dynamics is able to be done or possible to implement and it
is a practical way to add more security for identity
verification.
Guven, A. and I. Sogukpinar, proposed
“Understanding users keystroke patterns for computer
access security [4]” In this paper they have proposed
Computers & Secure User authentication is a major problem
in gaining access rights for computer resources. A recent
approach to improve the computer access rights is the use of
biometric properties as the keystroke rhythms of users.
Therefore user authentication for computers can be more
secure using keystroke rhythms as biometric authentication.
Methods like minimum distance, statistical, vector based,
neural network type and data mining techniques have been
applied for examining the keystroke patterns. In this paper, a
vector based algorithm for a recent approach has been
applied in the identification of keystroke patterns. Keystroke
Identification system that is a neuron physical characteristic
is studied to realize biometric authentication.
D. Gunetti and C. Picardi, proposed “Keystroke
analysis of free text, ACM Transactions on Information and
System Security [5]” In this paper they elaborate Keystroke
dynamics can be useful to discover personal identity
even after an authentication phase has been passed, provided
that we are able to deal with the typing rhythms of free text,
chosen and entered by users without any specific constraint.
In this paper we present a method to compare typing
samples of free text that can be used to verify personal
identity. We have tested our technique with a wide set of
experiments on 205 individuals, obtaining a False Alarm
Rate of less than 5&percent; and an Impostor Pass Rate of
less than 0.005&percent;. Different trade-offs are, however,
possible. Our approach can rely on what is typed by people
because of their normal job, and a few lines of text, even
collected in different working sessions, are sufficient to
reach a high level of accuracy, which improves relatively to
the amount of available information. As an inference, we
argue that our method can be useful in computer security as
a complementary or alternative way to user authentication
and as an relieve for intrusion detection.
D. Bartmann, I. Bakdi and M. Achatz proposed”
Design of an Authentication system based on Keystroke
Dynamics Using a Predefined Input Text. [6]” In this paper
they elaborate the design of an authentication system based
on keystroke dynamics is made difficult by the fact that the
typing behavior of a person is laid to strong fluctuations and
variations. An unsymmetrical method able to handle this
difficulty by using a long text on enrolment and a short one
at login is analyzed in this article. The results of an
empirical study based on an extensive field test are
presented. The study shows that the advantages of the
analyzed method remain even if a predefined input text is
used. The results also show that the method’s quality is
highly depends on the amount of text typed on enrolment as
well as on login, which makes the system scalable to
different security levels. They also confirm the importance
of using stable characteristics that are due, for example, to
the user’s right- or left-handedness. The method’s learning
velocity is shown to be high, which enables enrolment to be
kept short. Moreover, the study display that allowing
multiple login attempts which significantly improves the
recognition performance without sacrificing security.
F. Monrose and A. Rubin proposed “Authentication
via keystroke dynamics. [7]” In this paper they elaborate
more than ever before the Internet is changing computing as
we know it. Global access to information and resources is
becoming an integral part of nearly every aspect of our lives.
Unfortunately, with this global network access increased
chances of malicious attack and intrusion. In an effort to
deal with the new threats disclosed by the networking

(IJSRD/Vol. 3/Issue 10/2015/236)
revolution of the past few years reliable, rapid, and
unintrusive means for automatically recognizing the identity
of individuals are now being sought. In this paper we
examine an emerging non-static biometric technique that
aims to identify users based on analyzing usual rhythm
patterns in the way they type.
L. Breiman, “Random Forests” proposed ”Machine
Learning [8]” In this paper they elaborate More than ever
before the Internet is changing computing as we know it.
Global access to information and resources is becoming an
integral part of nearly every aspect of our lives.
Unfortunately, with this global network access come
increased chances of malicious attack and intrusion. In an
effort to deal with the new threats revealed by the
networking revolution of the past few years reliable, rapid,
and un-intrusive means for automatically recognizing the
identity of individuals are now being sought. In this paper
we examine an emerging non-static biometric technique that
aims to identify users based on analyzing regular rhythm
patterns in the way they type.
B. Existing Project Management System:
In most existing Project management system required
message passing or communication systems like email
system to maintain track of communication between
multiple users. And also they required manual updating in
task completion and ticket generation or other activity which
are performed by user itself. It also not is providing any
major security to PMS to secure projects important file
which are share between different users. There for we
proposed Keystroke Dynamics Authentication with Project
Management system.
IV. PROPOSED METHOD
As we see previous research on keystroke dynamics
authentication we proposed system is Keystroke Dynamics
Authentication with project Management System. The
purpose of this system is to secure or protect data from
unauthorized access. Keystroke Dynamics Authentication
with PMS system (KDAPMS System) work in three
sections in that first section has two phases first is training
phase and second is verification phase.
In first training phase of KDAPMS system when
user perform typing activity on any simple keyboard that
time generate three atomic event key up event, key down
event, and key press event. Using this atomic event
KDAPMS system extract user-temporal future like flight
time, interval time, latency time among this value we
consider one value which is identity of particular user which
stored. After in verification phase at user login time system
again generate keystroke identity of that user and check in
training set for authentication if it matches with its particular
identity then user directly switch to tired section otherwise
switch to second section, after three attempt by user for
identity.
V. CONCLUSION
The proposed web application provides security in term of
unique identification for particular users through its typing
pattern and also provide project management system. Hence,
we conclude that Keystroke Dynamics Authentication with
Project Management System is better than all traditional
existing keystroke dynamics system and project
management system.
ACKNOWLEDGMENT
The satisfaction that accompanies the successful completion
of any task would be incomplete without mentioning the
people who made it possible. We are grateful to a number of
individuals whose professional guidance along with
encouragement have made it very pleasant endeavor to
complete this survey.
It gives us great pleasure in presenting the
preliminary project report on ‘Keystroke Dynamics
Authentication with Project Management System.’ We
would like to take this opportunity to thank my internal
guide Prof. P. P. Kanhegaonkar for giving us all the help
and guidance we needed. We are really grateful to them for
their kind support. Their valuable suggestions were very
helpful.
We are also grateful to Prof. N. V. Alone, Head of
Computer Engineering Department, Gokhale Education
Society’s R. H. Sapat College of Engineering, Management
Studies Research, Nashik-5 for his indispensable support,
suggestions. In the end our special thanks to Dr. P. C.
Kulkarni (Principal of GESRHSCOEMSR)for providing
various resources such as laboratory with all needed
software platforms, continuous Internet connection, for Our
Project.
REFERENCES
[1] Tomer Shimshon, Robert Moskovitch, Lior Rokach,
Yuval Elovici “Clustering Di-Graphs for Continuously
Verifying Users according to their Typing Patterns”.
2014 IEEE 28-th Convention of Electrical and
Electronics Engineers in Israel.
[2] Tyler Highlander, D Ale Bassett, Derek Boone
“Utilization of Keyboard Dynamics for Unique
Identification of Human Users”.
[3] E. Yu, S. Cho. “Keystroke dynamics identity
verification - its problems and practical solutions”. 23
2004
[4] Guven, A. and I. Sogukpinar, “Understanding users
keystroke patterns for computer access security,” 22,
695-706, 2003.
[5] D. Gunetti and C. Picardi, “Keystroke analysis of free
text. ACM Trans. Inf. Syst. Secur”., 8(3):312–347,
2005.
[6] D. Bartmann, I. Bakdi and M. Achatz. “On the Design
of an Authentication system based on Keystroke
Dynamics Using a Predefined Input Text.”, 1(2), 1-12,
April-June 2007.
[7] F. Monrose and A. Rubin. “Authentication via
keystroke dynamics.”, 48–56 1997.
[8] L. Breiman, “Random Forests”, Machine Learning, vol
45(1) 2001.

Keystroke Dynamics Authentication with Project Management System

More Related Content

What's hot (20)

Viewers also liked (8)

Similar to Keystroke Dynamics Authentication with Project Management System (20)

More from IJSRD (20)

Recently uploaded (20)

Keystroke Dynamics Authentication with Project Management System