www.ijrit.com ISSN 2001-5569

Rishika Jain

, IJRIT 213

International Journal of Research in Information Technology (IJRIT)

www.ijrit.com www.ijrit.com www.ijrit.com

www.ijrit.com ISSN 2001-5569

Multibiometric E Multibiometric E Multibiometric E

Multibiometric E----Payment Card (MEC) Based on Payment Card (MEC) Based on Payment Card (MEC) Based on Payment Card (MEC) Based on Feature Level Fusion to Tackle ATM Fraud

Feature Level Fusion to Tackle ATM Fraud Feature Level Fusion to Tackle ATM Fraud Feature Level Fusion to Tackle ATM Fraud

Rishika Jain¹, Er. Abhishek choudhary² and Mr.Vikas Choudhary³

1MTech Scollar,Computer Science Department,Bhagwant University , Ajmer, Raj, India

[email protected]

2Assistant Professor, Computer Science Department,Bhagwant University , Ajmer, Raj, India

[email protected]

3Assistant Professor, Computer Science Department,Bhagwant University , Ajmer, Raj, India

[email protected]

Abstract

Today growth in e-transaction has been increased rapidly; there is a greater demand for reliable, authenticate and secure e-transaction. But number of problems associated with the implementation of a secure e-transaction. E-transaction requires a commitment to secure details, including debit card, credit card or other confidential information of the customers from various attacks such as man-in-the middle attack, phishing attack etc., To overcome the above attacks this research work propose a Mulibiometrics E-Payment Card (MEC) for ATM (Automated Teller Machine), play an important role which provide security solution against the well known breaches. This paper is focused on securing reliable authentication scheme through effective feature level fusion of biometric templates

Keywords: Automated Teller Machine (ATM),Fusion , Iris, Fingerprint, Multibiometric E-Payment Card

1. Introduction

ATMs are electronic banking machines located in different places and the customers can make basic transactions without the help of bank staffs. With the help of ATM the user can perform several banking activities like money transfer, cash withdrawal, credit card payment, paying various home usage bills like electricity, and phone bill. It is a more convenient for users to access their bank accounts and to conduct financial transactions. In recent years, with the wide utilization of internet technology it is necessary to raise ATM security. However, the internet communication will be exposed there by unwanted people allow to do different kinds of attacks on ATM System. Biometric based authentication is good solution which overcome the various security problems. Biometric characteristics of an individual are unique and therefore can be used to authenticate a user's access to ATM centres.Initial cases authentication in ATM centres are done with Unimodal Biometric methodologies. Unimodal biometric systems can be overcome by using multimodal biometric systems.[1]. A multimodal biometric system combines a variety of biometric

Rishika Jain

, IJRIT 214

identifies in making a personal identification and takes the advantage of the capabilities of each individual biometric.

A simple multimodal biometric system consists of four basic components:

1) Sensor module which acquires the biometric data.

2) Feature extraction module where the acquired data is processed to extract feature vectors.

3) Level of fusion where more no of vectors are integrated.

3) Matching module where feature vectors are compared against those in the template.

4) Decision-making module in which the user's identity is established or a claimed identity is accepted or rejected.

1.1 ATM Card

There are simply plastic card (54 mm by 85.6 mm by0.76 mm) ,with a microprocessor and memory embedded inside the card ,which is seen as golden plates, contact pads, at one corner of card.The magnetic stripes on many credit, banking and other types of cards use a strip of magnetic material to store digital data. A small amount of data is stored on the strip, including the cardholder's name, account number, expiration date,biometric template etc.

There are actually three tracks, or stripes of data along the magnetic strip of a ATM card. The most common standard includes:

• Track 1: 79 alphanumeric characters

• Track 2: 40 numeric characters

• Track 3: Less commonly used, allows 108 numeric characters.

Fig .1 A sample of ATM card

That data is encoded as a series of ones and zeros along the magnetic strip. The code can be storedin a file as small as 100 bytes-which fits easily onto the magnetic stripe of a credit or debit card. By encoding data on the magnetic stripe, data can be entered into a computer with a single swipe.

1.2 Types of ATM Attacks

No. ATM Attacks Explanation

1.

This involves placing a device directly over or into the ATM card reader slot. The criminals have to withdraw the whole device each time a card is trapped.

PIN Cracking

A bank insider could use an existing Hardware Security Module (HSM) to reveal

Rishika Jain

, IJRIT 215

2.

insider of a third-party Switching provider could attack a bank outside of his territory or even in

another continent.

3.

Phishing scams are designed to entice the user to provide the card number and PIN for their bank card. The attacker can either take the copy and make paper counterfeit checks, or take that information and create PayPal accounts or other online payment accounts that will leave the victim on the hook for any purchases.

4.

.

Malware attacks required an insider, such as an ATM technician who has a key to the machine, to place the malware on the ATM.

The malware lets criminals take over the ATM to steal data, Pins and cash.

2. Proposed Multibiometric E-Payment Card 2.1 Motivation

No individual trait can provide 100% accuracy. Further, the results generated from the individual traits are good but the problem arises in finger print recognition based ATM system when finger print scars and cuts. Thus , the system takes noisy finger print as input which is not able to extract the minutiae points correctly and in turns lead to false acceptance rate(FAR) increase.Similary the problem faced by Iris based ATM system .The user is not able to give his iris image due to problem in exposure to light or some diseases exist. Thus to overcome the problem faced by iris and finger print, a novel combination is proposed for recognition system This integration of binary code generate from iris and finger template provide anti spoofing measure by making it difficult for an intruder to spoof multiple biometric template simultaneously and protect from various ATM frauds.

2.2 Design Methodology of MEC Construction

Enrollment-The objective of this enrollment process is to create a MEC card of the user. , the biometric traits of the individual is captured during the enrollment process (e.g., using a sensor for fingerprint, camera for iris recognition). The unique features are then extracted from the biometric sample and create the user’s biometric template. This biometric template is stored in a database and on a machine- readable ID card for later use during a matching process.

Fig. 2 Enrollment process of MEC card Construction

Feature Extraction

Feature Extraction

Feature Fusion Set

Data on MEC Card

Rishika Jain

, IJRIT 216

Verification –Once the individual has been enrolled in the system . Now he can start to access the account or transaction from ATM after verification process succeed. The biometric samples(Iris and Finger) provided by the user during verification process The unique features are extracted from the biometric sample to create the user’s “live” biometric template.This new template is then compared with the template(s) previously stored and a numeric matching(similarity) score(s) is generated based on a determination of the common elements between the two templates. System designers determine the threshold value for this verification score based upon the security and convenience requirements of the system.

Fig. 3 Verification process

2.3 Proposed Flow Diagram of ATM Working

After the card’s magnetic strip store binary code of card holder and biometric template during enrolment process. In order to perform transaction into the ATM machine, the user swipe the card to the card reader and then ask to provide PIN .If pin is match with the registered Pin then ask to upload finger and Iris .After accepting the image by the ATM match upload biometric templates with the MEC card. If user is authenticate, transaction is perform otherwise terminate the user from the system.

Feature Extraction

Feature Extraction

Feature Fusion Set

Live Template

Matching 95 %

Perform Transaction Biometric

Matching Template

Extraction

Rishika Jain

, IJRIT 217

Fig. 4 Flow Chart of Working process of ATM

3. Implementation

The implementation has been done with the help of above diagrams .All experiments are done on an intel Pentium dual core processor, with 2GB RAM and 160GB hard disk. In the software requirements windows XP operating system has been used. For front end designing purpose Visual studio 2008, and for back end data storage purpose SQL server 2005 has been used. The development language C# has been used.

Match?

Perform Transaction

Terminate Lock Card

fusion Binary code

load finger and iris

from card

Scan Iris&Finger image

Correct Pin?

Attempt exceeds

limit?

Start verification

Scan card to reader

Card Valid Or Properly

inserted?

Insert Pin No

O

Yes

Yes

Rishika Jain

, IJRIT 218 4. Conclusion

In conclusion, using ATM cards with biometrics results in a trusted credential for authenticating an individual’s identity using one-to-one biometric verification. With the biometric template stored on the smart card, comparison can be made locally, without the need for connection to a database of biometric identifiers. The chance given for hackers to make use of fake biometrics to act as an authorized user is strictly avoided, which makes the ATM system more secure , But the cost spend to design and implement this type of system is higher when compared to the existing ATM system.

Acknowledgments

The author would like to thanks the guide Mr. Abhishek choudhary for his valuable suggestion in publishing the paper and special thanks to Mr.Vikas Choudhary(HOD) who support me in publishing paper and thank the anonymous reviewers for their valuable comments.

References

[1] S.S.Das and Debbarma “Designing a Biometric Stradegy fingerprint Measure for enhancing ATM Security in Indian e-banking system”,International Journal of Information and Communication Technology Research,volume.1,no.5,pp.197-203,2011.

[2] C. Tilborg (Ed). Encyclopedia of Cryptography and Security. Springer, 2005.

[3] Gang Zheng, Wanqing Li and Ce Zhan, "Cryptographic Key Generation from Biometric Data Using Lattice Mapping", in Proceedings of the 18th International Conference on Pattern Recognition, vol.4, pp.

513 - 516,2006..

[4] S. Zhang, C. Zhu, J. K. O. Sin, and P. K. T. Mok, “A novel ultrathin elevated channel low-temperature poly-Si TFT,” IEEE Electron Device Lett., vol. 20, pp. 569–571, Nov. 1999.

[5] John Daugman, “How Iris Recognition Works”, in Proceedings of International Conference on Image Processing, vol.1, pp. I-33- I-36,2002.

[6] D. Maltoni, D. Maio, A. K. Jain, and s. Prabhakar, Handbook of Fingerprint Recognition, Springer- Verlag, 2003

[7] Yan Yan and Yu-Jin Zhang , "Multimodal biometrics fusion using Correlation Filter Bank", in proceedings of the 9th International Conference on Pattern Recognition, pp. 1-4,Tampa, FL, 2008.

[8] Andrew Teoh Beng Jin, David Ngo Chek Ling, Alwyn Goh,”Biohashing : two factor authentication featuring fingerprint data and tokenized random number “ April 2004,”The Journal Of The Pattern Recognition Society “ , Elsevier , April 2004.

[9] M. Subha, S. Vanithaasri,” A study on authenticated admittance of ATM Clients using biometrics based cryptosystem”, International Journal of Advances in Engineering and Technology, Vol 4,Issue 2,pp 456-463,2012.

[10] S. Pravinthraja , Dr.K. mamaheswari,” Multimodal Biometrics for Improving Automatic Teller Machine Security”, International Journal of Advances in Image processing, Vol 1,special issue, pp 19-25 , 2011.