International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 3 | Mar -2017
p-ISSN: 2395-0072
www.irjet.net
TRANSPARENT DEVELOPMENTAL BIOMETRIC BASED SYSTEM PROTECT USER REAUTHENTICATION USING SMARTPHONES *1
*1,2,3 B.Tech
Mr. R.Arunkumar, *2 M.Arunraj, *3 R.Prabhakaran, *4 Mr.V.Naveen
Student, Department of Information Technology Kingston Engineering College, Christainpettai, Katpadi, Vellore.
*4 Assistant
Professor, Department of Information Technology Kingston Engineering College, Christainpettai, Katpadi, Vellore.
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - With the emergence of smartphones as an
essential part of daily life, the demand for user reauthentication has increased manifolds. The effective and widely practiced biometric schemes are based upon the principle of “who you are” which utilizes inherent and unique characteristics of the user. In this context, the behavioral biometrics such as sliding dynamics make use of on-screen sliding movements to infer the user’s patterns. In this paper, we present Safeguard, an accurate and efficient smartphone user reauthentication (verification) system based upon onscreen finger movements.. The key feature of the proposed system lies in fine-grained on-screen biometric metrics, i.e., sliding dynamics and pressure intensity, which are unique to each user under diverse scenarios. We first implement our scheme through five machine learning approaches and finally select the support vector machine (SVM)-based approach due to its high accuracy. We further analyze Safeguard to be robust against adversary limitation. We validate the efficacy of our approach through implementation on off-the-shelf smartphone followed by practical evaluation under different scenarios.
Key Words: SVM, honeybeeandantcolony, FAR,FRR, reauthentication with smart phone, Mobile Verification. I. INTRODUCTION Mobile Devices, especially smartphone, becomes the most common used tools for human daily accessing mobile social networks (MSNs) [1]-[3]. Thus, preserving users' privacy and sensitive data grows to the urgent need as smartphones store users' more private and sensitive information. At present, many smartphone authentication © 2017, IRJET
|
Impact Factor value: 5.181
|
schemes are With the introduction of the Android operating system for mobile phones, an alternative to PINauthentication on mo-bile devices was introduced and widely deployed for the first time. The password pattern, similar to shape-based authentication approaches. Despite its manifold advantages, this approach has major drawbacks, the most important one being security. Drawn passwords are very easy to spy on [11,36], which makes shoulder surfing, a common attack in public settings [27], a serious threat. Other attacks include the infamous smudge attack [1], in which finger traces left on the screen are used to extract the password. Due to its weak security properties, this authentication approach does not fully meet the requirement of adequately protecting the user’s data stored on the device. Nowadays, not only private but also valuable business information is stored on the user’s handheld [10]. Therefore, resistance to attacks is a major concern when designing respective authentication systems. The biometric-based authentication has been widely used in many applications such as access control and continuous tracking systems [5]. However, the reauthentication is still challenging on smartphones. The reason lies in three-folds: 1) Current biometric approaches, such as fingerprints and retinal [6] scans, provide accurate one-time authentication but require specialized hardware, which may be nontransparent, expensive, or unavailable for smartphones. 2) A typical smartphone is equipped with a touch screen as the user interface. Thus, the classical behavioral biometrics on PCs, such as keystroke and mouse dynamics, cannot be applied on smartphones for user verification. 3) Existing reauthentication schemes for smart-phone are not practical for real applications because of low accuracy [7], limited application scenarios [8] or high system overhead [10]. Moreover, most existing approaches only address the one-time authentication when users unlock the screen of the smartphones. .
ISO 9001:2008 Certified Journal
|
Page 591