You are on page 1of 28

CRYPTOGRAPHIC KEY GENERATION FROM

FINGERPRINT BIOMETRICS

seminar report submitted


in partial fulfillment of the requirement for award of the degree of

Bachelor of Technology
in
Computer Science & Engineering

By

G.BHARGAVA KUMAR (19UECS0356)


M. VISHAL GOUD (19UECS0579)
P.AJAY KUMAR (19UECS0797)

Under the guidance of


Dr.A.Suresh, M E.,Ph.D
Assistant Professor

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING


SCHOOL OF COMPUTING

VEL TECH RANGARAJAN Dr.SAGUNTHALA R&D


INSTITUTE OF SCIENCE AND TECHNOLOGY
(Deemed to be University Estd u/s 3 of UGC Act, 1956)
CHENNAI 600062, TAMILNADU, INDIA
June, 2022
BONAFIDE CERTIFICATE
It is certified that the work contained in the seminar report titled ”CRYPTOGRAPHIC
KEY GENERATION FROM FINGERPRINT BIOMETRICS” by ”G.BHARGAVA
KUMAR (19UECS0356) M.VISHAL GOUD (19UECS0579) P.AJAY KUMAR
(19UECS0797)” has been carried out under my supervision and that this work has
not been submitted elsewhere for a degree.

Signature of Supervisor
Dr.A.Suresh, M E.,Ph.D
Assistant professor
Computer Science & Engineering
School of Computing
Vel Tech Rangarajan Dr.Sagunthala R&D
Institute of Science and Technology
June, 2022

Signature of Head of the Department


Dr. V. Srinivasa Rao
Professor & Head
Computer Science & Engineering
School of Computing
Vel Tech Rangarajan Dr.Sagunthala R&D
Institute of Science and Technology
June, 2022

i
DECLARATION
We declare that this written submission represents our ideas in our own words and
where others’ ideas or words have been included, we have adequately cited and ref-
erenced the original sources. We also declare that we have adhered to all principles
of academic honesty and integrity and have not misrepresented or fabricated or fal-
sified any idea/data/fact/source in our submission. We understand that any violation
of the above will be cause for disciplinary action by the Institute and can also evoke
penal action from the sources which have thus not been properly cited or from whom
proper permission has not been taken when needed.

(Signature)
((G.BHARGAVA KUMAR)
Date: / /

(Signature)
(M.VISHAL GOUD)
Date: / /

(Signature)
(P.AJAY KUMAR)
Date: / /

ii
APPROVAL SHEET

This seminar report entitled (CRYPTOGRAPHIC KEY GENERATION FROM FIN-


GERPRINT BIOMETRICS) by (G.BHARGAVA KUMAR (19UECS0359), (M.Vishal
Goud (19UECS0579), (P.Ajay Kumar (19UECS0797) is approved for the degree of
B.Tech in Computer Science & Engineering.

Signature of Supervisor
Dr.A.Suresh, M E.,Ph.D
Assistant Professor
Computer Science & Engineering
School of Computing
Vel Tech Rangarajan Dr.Sagunthala R&D
Institute of Science and Technology

Signature of Seminar Handling Faculty


Dr.A.Peter Soosai Anandaraj.,B.E.,M.E.,Ph.D
Assistant Professor
Computer Science & Engineering
School of Computing
Vel Tech Rangarajan Dr.Sagunthala R&D
Institute of Science and Technology

Date: / /
Place:

iii
ACKNOWLEDGEMENT
We express our deepest gratitude to our respected Founder Chancellor and Pres-
ident Col. Prof. Dr. R. RANGARAJAN B.E. (EEE), B.E. (MECH), M.S (AUTO).
DSc., Foundress President Dr. R. SAGUNTHALA RANGARAJAN M.B.B.S.,
Chairperson Managing Trustee and Vice President.

We are very grateful to our beloved Vice Chancellor Prof. S. SALIVAHANAN,


Ph.D., for providing us with an environment to complete our seminar successfully.

We record indebtedness to our Dean & Head, Department of Computer Science


& Engineering Dr. V. SRINIVASA RAO, M.Tech., Ph.D., for immense care and
encouragement towards us throughout the course of this seminar.

We take this opportunity to express our gratitude to Our Internal Supervisor Su-
pervisor name,degree.,(in capital letters) for his/her cordial support, valuable in-
formation and guidance, he/she helped us in completing this seminar through various
stages.

A special thanks to our Seminar Coordinator Dr. G. Tamilmani, Ph.D., for her
valuable guidance and support throughout the course of the seminar.

We thank to our Seminar handling Faculty (Faculty name,degree.,(in capital


letters)) for the valuable information shared in proceeding with our seminar.

We thank our department faculty, supporting staff and friends for their help and
guidance to complete this project.

G.BHARGAVA KUMAR (19UECS0356)


M. VISHAL GOUD (19UECS0579)
P.AJAY KUMAR (19UECS0797)

iv
ABSTRACT

Cryptographic techniques play a major role in digital information se-


curity. In cryptography, securing / storing the cryptographic key is an
arduous task. The proposed stable cryptographic key generation di-
rectly from fingerprint biometrics overcomes this security concern. It
eradicates the need of storing a cryptographic key. Rather, the key
can be generated from a fingerprint biometrics on a need basis. In
this work, a novel gray code based method is introduced to generate
a stable cryptographic key from fingerprint. Usage of gray code rep-
resentation significantly reduces the number of mismatch bits between
the generated bit strings from the two instances of the same fingerprint.
Hence, Reed Solomon error correction code is able to successfully cor-
rect the errors which may occur due to variations in captured images of
the same fingerprint. This generated bit string is used in a symmetric
key setup for secure data storage
Keywords:Cryptographic Key; Key Generation; Bio-Cryptosystems;
Fingerprint; Biometrics; Secure Storage; Reed-Solomon Code;
Gray Code.

v
LIST OF FIGURES

1.1 Symmetric-Encryption . . . . . . . . . . . . . . . . 3
1.2 Asymmetric-Encryption . . . . . . . . . . . . . . . . 4

4.1 Minutiae Extraction . . . . . . . . . . . . . . . . . . 10


4.2 Binary Code Analysis . . . . . . . . . . . . . . . . . 13
4.3 Gray Code Analysis . . . . . . . . . . . . . . . . . . 13

vi
LIST OF ACRONYMS AND
ABBREVIATIONS

DRP Data Retrieval Process


SSP Secure Storage Process
ME Minutiae Extraction
IBE Identity-based encryption
GC Gray Code
BC Binary Code

vii
TABLE OF CONTENTS

Page.No

ABSTRACT v

LIST OF FIGURES vi

LIST OF ACRONYMS AND ABBREVIATIONS vii

1 INTRODUCTION 1
1.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Aim of the Seminar . . . . . . . . . . . . . . . . . . . 2
1.3 Scope of the Seminar . . . . . . . . . . . . . . . . . . 2
1.4 Methodology . . . . . . . . . . . . . . . . . . . . . . 2
1.4.1 Symmetric Cryptography . . . . . . . . . . . . 2
1.4.2 Asymmetric Cryptography . . . . . . . . . . . 3

2 LITERATURE REVIEW 5

3 SEMINAR DESCRIPTION 7
3.1 Existing System of Disadvantages . . . . . . . . . . . 7
3.2 Advantages . . . . . . . . . . . . . . . . . . . . . . . 8
3.3 Feasibility Study . . . . . . . . . . . . . . . . . . . . 8

4 METHODOLOGIES 9
4.1 Proposed System . . . . . . . . . . . . . . . . . . . . 9
4.1.1 Secure Storage Process . . . . . . . . . . . . . 9
4.1.2 Minutiae Extraction . . . . . . . . . . . . . . 10
4.1.3 Cryptographic Key Generation Using Gray Code 11
4.1.4 Euclidean Distance Between Pair of Minutiae
Points . . . . . . . . . . . . . . . . . . . . . . 11
4.1.5 Sorting the Distances . . . . . . . . . . . . . . 12
4.1.6 Converting Euclidean Distance into Gray Code 12
4.1.7 Concatenation of Gray Codes to Generate the
Key . . . . . . . . . . . . . . . . . . . . . . . 12

5 RESULTS AND DISCUSSIONS 14

6 CONCLUSION AND FUTURE ENHANCEMENTS 15


6.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . 15
6.2 Future Enhancements . . . . . . . . . . . . . . . . . . 16

References 16
Chapter 1

INTRODUCTION

1.1 Introduction

Information security today is becoming more and more important.


Cryptography is an important feature of computer and network secu-
rity. Many cryptographic algorithms are available for securing infor-
mation. Conventional cryptography authenticates messages based on
the key but not on the user. Hence unable to differentiate between
the legitimate user an attacker. These keys can be guessed or cracked.
Large size of strong keys results in longer delay in encryption/decryp-
tion. It is difficult to remember the keys, storing them in a data base
may be insecure.A gray code based encoding is used to generate a sta-
ble cryptographic key from fingerprint biometrics. It is the first attempt
to generate a stable cryptographic key using gray code. ReedSolomon
error correction code is used to correct the errors arising due to bio-
metric variance to provide stability to the generated cryptographic key.
According to the proposed scheme, neither the biometric information
nor the generated cryptographic key is stored. Therefore, blended sub-
stitution attack, key inversion attack and attack via record multiplicity
are not possible. The reconstruction of original biometric is not pos-
sible too. This approach generates two distinct cryptographic keys
for two different users. Therefore, the chance for producing the same

1
cryptographic key by a genuine user and an impostor is eradicated.
The randomness test and the various security analysis methods ensure
the security of the generated cryptographic key. Finally, this crypto-
graphic key is used in a symmetric key set up for secure storage of
sensitive data.

1.2 Aim of the Seminar

The main aim of the project is to generate a stable cryptographic key


from fingerprint biometrics using gray code for secure storage.

1.3 Scope of the Seminar

The main scope the project is neither the generated cryptographic


key nor the biometric template is stored. It ensures privacy, confiden-
tiality, integrity and authenticity.

1.4 Methodology

Instead of using PINs and passwords as cryptographic keys that are


either easy to forget or vulnerable to dictionary attacks, easy-to-carry
and difficult-to-transfer keys can be generated based on user-specific
biometric information.

1.4.1 Symmetric Cryptography

Secret Key Cryptography, or symmetric cryptography, uses a sin-


gle key to encrypt data. Both encryption and decryption in symmetric

2
cryptography use the same key, making this the easiest form of cryp-
tography. The cryptographic algorithm utilizes the key in a cipher to
encrypt the data, and when the data must be accessed again, a person
entrusted with the secret key can decrypt the data. Secret Key Cryptog-
raphy can be used on both in-transit and at-rest data, but is commonly
only used on at-rest data, as sending the secret to the recipient of the
message can lead to compromise.

Figure 1.1: Symmetric-Encryption

1.4.2 Asymmetric Cryptography

Public Key Cryptography, or asymmetric cryptography, uses two


keys to encrypt data. One is used for encryption, while the other key
can decrypts the message. Unlike symmetric cryptography, if one key
is used to encrypt, that same key cannot decrypt the message, rather
the other key shall be used.One key is kept private, and is called the
“private key”, while the other is shared publicly and can be used by
anyone, hence it is known as the “public key”. The mathematical re-
lation of the keys is such that the private key cannot be derived from

3
the public key, but the public key can be derived from the private. The
private key should not be distributed and should remain with the owner
only. The public key can be given to any other entity.

Figure 1.2: Asymmetric-Encryption

4
Chapter 2

LITERATURE REVIEW

[1] Z., Teoh, A.B.J., Goi, B.M., Tay, Y.H.: Biometric cryptosystems:
a new biometric key binding and its implementation for fingerprint
minutiae-based representation. Pattern Recogn. 56, 50–62 (2016). If
an attacker is able to recover the secret cryptographic key through so-
cial engineering or dictionary attacks, it is possible to recover the bio-
metrics in a key binding scheme usingthe cryptographic key and the
helper data (Scheirer and Boult, (2007); Tams et al., (2015).
[2] In Barman et al., (2015), distances between every pair of minu-
tiae points are estimated. Subsequently, unique distances are sorted in
ascending order. A binary string is generated whose length equals to
the maximum distance value. If the index value of an element in the
string is present in the sorted sequence of distances, then the bit in the
string at the index position is set as 1. If the index value is not present
in the sorted sequence of distances, then the concerned bit is set as
0. A random permutation of this binary string is used as the crypto-
graphic key. The permuted bit positions of the binary string are stored
as helper data.
[3] In Panchal and Samanta, (2016), the fingerprint image is parti-
tioned into a set of nonoverlapping blocks. The minutiae points are
extracted from each block. Every pair of minutiae points from two
5
neighboring blocks is joined using straight line. Lengths and orien-
tations of these straight lines are calculated. From these length and
orientation values, the length and angle ratios are calculated and are
converted into binary string. Length ratios are calculated by consider-
ing the ratio of lengths of each pair of straight lines. The angle ratios
are also calculated similarly by considering the ratio of angles / orien-
tations of each pair of straight lines.
[4]In Panchal and Samanta, (2018), the binary representations of
orientation angle and length of each straight line are XORed. Then,
these XORed strings of all straight lines are concatenated. A sequence
of substitution, expansion and permutation of the concatenated string
generates a cryptographic key. The length and the angle values of
these straight lines are used to generate a helper data. Involvement
of orientation of a line joining two minutiae points makes these two
schemes unacceptable against rotation of fingerprint.

6
Chapter 3

SEMINAR DESCRIPTION

3.1 Existing System of Disadvantages

In all of the above methods, a helper data is used to regenerate the


cryptographic key. But helper data based cryptographic key genera-
tion methods are vulnerable to masquerade attack, replay attack, hill
climbing attack, attack via record multiplicity and brute force attack
. Another weakness of these schemes is that the reconstruction of the
original biometrics from the stored helper data may be possible. Exist-
ing approaches can be grouped into two buckets based on number of
users whose fingerprint are used to generate a cryptographic key Sev-
eral approaches need fingerprints from two users; Sarkar and Singh,
(2021)). These approaches are mainly used to generate keys from the
the fingerprints of a sender and a receiver for a secure communication.
As the focus of this current paper in to generate a symmetric key for se-
cure storage, these approaches are not applicable for the said task. (2)
Several approaches generate the key from fingerprint of a single user
(e.g., Suresh et al., (2019); Wang et al., (2021)). These approaches can
be used to the task at ahand, i.e., to generate a cryptographic key for
secure storage

7
3.2 Advantages

-less memory
-Confidentiality
-Authentication

3.3 Feasibility Study

Cryptographic key is neither shared nor stored anywhere. As a sin-


gle key is generated from an user’s biometrics, this can be used for
secure storage of data using a symmetric key setup. The generated key
is used to encrypt the data which is stored in a secure vault. The same
biometrics is used for regenerating the cryptographic key so that the
previously encrypted data can be decrypted. Every time the crypto-
graphic key is obtained using the biometrics on the fly. As the key is
neither being shared nor stored, the key cannot be stolen.

8
Chapter 4

METHODOLOGIES

4.1 Proposed System

In this work, an effort is made to generate a stable cryptographic


key directly from user’s fingerprint biometrics. Moreover, a scheme is
suggested for secure storage of sensitive personal data using this gen-
erated stable cryptographic key. An overview of secure data storage
and retrieval process using a stable cryptographic key being generated
from fingerprint biometrics is diagrammatically. The detailed steps for
the proposed secure storage and retrieval processes are discussed in
this section.

4.1.1 Secure Storage Process

Secure storage of individual’s sensitive personal data can be achieved


through encryption of the data using a secret key in a symmetric en-
cipherment process. In this work, a method to generate this secret
key from an individual’s fingerprint is proposed using gray code based
encoding. Moreover, a Reed-Solomon error correction code is used
to ensure that the secret key is stably regenerated. The major steps
include minutiae extraction, cryptographic key generation using gray

9
code, usage of Reed-Solomon code to generate parity symbols and en-
cryption of the sensitive personal data. Each step is discussed in detail
as given below.

Figure 4.1: Minutiae Extraction

4.1.2 Minutiae Extraction

Minutiae points in a fingerprint uniquely characterize each individ-


ual. Hence, accurate extraction of minutiae points from a captured
fingerprint image is necessary to generate a stable cryptographic key
for each individual. Some pre-processing steps such as contrast en-
hancement, binarization and thinning are performed on a captured fin-
gerprint image to correctly extract the set of minutiae points. Contrast
enhancement helps to detect the minutiae points easily by improving
the quality of the fingerprint image. It reduces the undesired effects of
incipient ridges, blurs, pores, scars and creases. Binarization converts
the fingerprint gray scale image containing the ridges and valleys into
a binary image. Various patterns of lines across the fingerprint image
are known as ridges. Spaces between these ridges are called as valleys

10
or furrows. The widths of the binarized ridge lines are reduced into
1-pixel using thinning. Minutiae points are extracted from a thinned
binary image. There exists varieties of minutiae points in a fingerprint
image like lake, island, ridge bifurcation, ridge ending, dots, pore, core
point, delta point, crossover, etc. Ridge bifurcation and ridge ending
are most widely accepted minutiae points

4.1.3 Cryptographic Key Generation Using Gray Code

Consistent Selection of Minutiae Points


Due to biometric uncertainty in capturing the same biometric sig-
nal, two acquired images of same fingerprint may not be always same.
Hence, the acquired images do not have exactly the same set of minu-
tiae points. Obtaining a stable cryptographic key from fingerprint bio-
metrics is the main objective of this proposed work. Hence, a con-
sistent set of minutiae A Stable Cryptographic Key Generation from
Fingerprint Biometrics 11 points must be used for key generation. In
this work, a consistent set of minutiae points is manually selected to
generate a stable cryptographic key from the common region of all
the fingerprint images of the same subject. Alternative approaches of
extracting minutiae points from the consistent region of a fingerprint

4.1.4 Euclidean Distance Between Pair of Minutiae Points

Euclidean distance between each pair of minutiae points is calcu-


lated from the selected consistent set of minutiae points. Let two
minutiae points Pi and Pj be located in the coordinates (xi , yi) and
(xj , yj ), respectively. The Euclidean distance between this pair of
minutiae points is computed as: di,j = q (xi xj ) 2 + (yi yj ) 2 (1)
Euclidean distance between pair of minutiae points is considered here
11
due to its rotational and translational invariance. In-spite of rotation
and translation induced changes in the absolute coordinate values of
the minutiae points, the distance between each pair of minutiae points
does not vary. Hence, it does not affect the stable cryptographic key
generation process.

4.1.5 Sorting the Distances

Sorting the Distances IfN minutiae points are finally selected from
a fingerprint, N C2 such distances are calculated from the coordinate
values of selected consistent set of minutiae points. To generate the
consistent key bit string, these N C2 Euclidean distance values are
sorted in ascending order.

4.1.6 Converting Euclidean Distance into Gray Code

Each Euclidean distance in the sorted sequence is converted into an


m-bit binary number. Then the m-bit binary number is converted into
m-bit gray code. Gray code is a reflected binary code in which two
successive values differ in only one bit. Gray code provides a major
advantage to this proposed work. Due to biometric uncertainty, if there
is slight change in the distance value, then there will be only minimum
change on the generated bit string. Therefore, it can be easily corrected
using error correction codes.

4.1.7 Concatenation of Gray Codes to Generate the Key

Concatenation of Gray Codes to Generate the Key The m-bit repre-


sentations of each gray code are concatenated to attain a single key bit
string which acts as the cryptographic key. It is to be noted that there

12
exist N C2 distance values for the selected N minutiae points. Hence,
the length of key is m × N C2 bits.

Figure 4.2: Binary Code Analysis

Figure 4.3: Gray Code Analysis

13
Chapter 5

RESULTS AND DISCUSSIONS

The proposed system is based on the Random forest Algorithm that


creates many decision trees. Accuracy of proposed system is done
by using random forest gives the ouput approximately 76 to 78 per-
cent. Random forest implements many decision trees and also gives
the most accurate output when compared to the decision tree. Random
Forest algorithm is used in the two phases. Firstly, the RF algorithm
extracts subsamples from the original samples by using the bootstrap
resampling method and creates the decision trees for each testing sam-
ple and then the algorithm classifies the decision trees and implements
a vote with the help of the largest vote of the classification as a final re-
sult of the classification. The random Forest algorithm always includes
some of the steps as follows: Selecting the training dataset:Using the
bootstrap random sampling method we can derive the K training sets
from the original dataset properties using the size of all training set the
same as that of original training dataset. Building the random forest
algorithm: Creating a classification regression tree each of the boot-
strap training set will generate the K decision trees to form a random
forest model, uses the trees that are not pruned.

14
Chapter 6

CONCLUSION AND FUTURE


ENHANCEMENTS

6.1 Conclusion

In cryptography, storing the cryptographic key is an arduous task.


The proposed stable cryptographic key generation directly from fin-
gerprint biometrics overcomes this security concern. It eradicates the
need of storing a cryptographic key. Rather, the key can be gener-
ated from a fingerprint biometrics on a need basis. In this proposed
approach, a stable key string is generated from the fingerprint image.
Hence, Reed-Solomon error correction code successfully corrects the
errors which may occur due to variations in captured images of the
same fingerprint. It has also been experimentally concluded that it is
impossible for an impostor to generate the same key as a genuine user.
Moreover, it is shown through randomness test of the generated bit
string that the generated bit string is random.

15
6.2 Future Enhancements

Identity-based encryption (IBE) is one of the most popular user au-


thentication and authorization method in the field of cryptography. We
have used JPBC library as a tool to implement IBE approach. This
paper presents an improved IBE method which takes lesser time as
compared to the competitive approach. One of the most important fea-
tures of the proposed approach is that it hides the user identity by using
Lagrange coefficient which consists of polynomial interpolation func-
tion. Security of the approach depends on the hardness of computing
bilinear Diffie-Hellman problem. This approach can also be imple-
mented without using bilinear pairing for further enhancement in time
complexity of key generation, encryption, and decryption.

16
Reference

[1] Anees, A., and Chen, Y-P. P. (2018) ’Discriminative binary fea-
ture learning and quantization in biometric key generation’, Pattern
Recognition, Vol. 77, pp.289–305.

[2] Barman, S., Samanta, D., and Chattopadhyay, S. (2015a) ’Ap-


proach to cryptographic key generation from fingerprint biomet-
rics’, International Journal of Biometrics, Vol. 7, No. 3,.

[3] Chang, D., Garg, S., Ghosh, M. and Hasan, M. (2020)


’BIOFUSE: A framework for multibiometric fusion on bio-
cryptosystem level’, Information Sciences, Vol. 546, pp.985–998.
https://doi.org/10.1016/j.ins.2020.08.065.

[4] Juels, A., and Wattenberg, M. (1999) ’A fuzzy commitment


scheme’, ACM Conference on Computer and Communications Se-
curity, pp.28–36.

[5] Mahendran, R. K., and Velusamy, P. (2020) ’A secure fuzzy extrac-


tor based biometric key authentication scheme for body sensor net-
work in Internet of medical things’, Computer Communications,
Vol. 153, pp. 545–552.

[6] Hoque, S., Fairhurst, M., and Howells, G. (2008) ’Evaluating bio-
metric encryption key generation using handwritten signatures’,
ECSIS Symposium on Bio-inspired, Learning.

17
18

You might also like