SlideShare ist ein Scribd-Unternehmen logo
1 von 19
Downloaden Sie, um offline zu lesen
Anti-Spoofing Algorithms for
Fingerprint Systems
Emanuela Marasco
12
Lane Department of Computer Science and Electrical Engineering
Security of Fingerprint Systems
13
[1] http://nexidbiometrics.com/brazilian-doctor-arrested-for-using-fake-fingerprints/
[2] http://secureidnews.com/news-item/apples-touch-id-spoofed/
• What about Impersonation?
• March 2013, Brazilian doctor accused to use spoof fingerprints to
check-in co-workers not present at work place
• September 2013, the iPhone5S equipped with Touch ID sensor
accepted a spoof fingerprint as live
Police recovered six silicone fingers
After two days only it was released
Fingerprint Spoofing
• Liveness detection distinguishes live human biometric presentations
from spoof artifacts [2],[3],[4]
• The liveness of a fingerprint is assessed by a numerical entity
14
[1] T. Matsumoto, H. Matsumoto, K. Yamada, and S. Hoshino. Impact of artificial gummy fingers on fingerprint systems. Optical Security and Counterfeit
Deterrence Techniques IV, 4677:275–289, January 2002.
[2] S. Schuckers. Spoofing and anti-spoofing measures. Information Security Technical Report, 7(4):56–62, 2002.
Making artificial fingerprints directly from a live finger [1]
• Fingerprint systems are vulnerable to spoof presentations [1]
[3] D. Yambay, L. Ghiani, P. Denti, G. Marcialis, F. Roli and S. Schuckers. LivDet 2011 – Fingerprint Liveness Detection Competition 2011. The 5th
International Conference on Biometrics (ICB), pages 208-215, March 2012.
[4] G. Marcialis, A. Lewicke, B. Tan, P. Coli, D. Grimberg, A. Congiu, A. Tidu, F. Roli, and S. Schuckers. First international fingerprint liveness detection
competition (LivDet09). The 15th International Conference on Image Analysis and Processing (ICIAP), pages 12–23, September 2009.
The considered dangerous scenarios
15
http://www2.washjeff.edu/users/ahollandminkley/Biometric/index.htmlThe images are taken from
• A person enrolls using a live finger
• A spoof artifact of the true finger is used during verification [1]
live spoof
Enrollment Verification
[1] S. Schuckers. Spoofing and anti-spoofing measures. Information Security Technical Report, 7(4):56–62, 2002.
Live or Spoof?
16
Images taken from LivDet09
Vulnerability Degree vs. Fingerprint Sensing
17
• Optical sensors: light entering the prism is reflected at valleys
and absorbed at the ridges
• Physiological vulnerability: materials with light reflectivity similar
to that of the skin
• Device: differences in ergonomics, arrangement of elements
• Capacitive sensors: the finger is modeled as the upper electrode
of a capacitor
• Fingerprint in gelatin are more dangerous
Spoof fingerprints obtained using the
same material (silicone) but scanned
by two different optical devices
(CrossMatch and Biometrika from
LivDet09
How to make Fingerprint Spoof?
18
• Materials which can be scanned (e.g., play-doh, gelatin, …)
[1] S. Schuckers. Spoofing and anti-spoofing measures. Information Security Technical Report, 7(4):56–62, 2002.
Known Spoofing Methods
19
Liveness Detection Approaches
20
Texture-based Features
21
Original Image De-noised Image Residual Noise
Original Image De-noised Image Residual Noise
L
I
V
E
S
P
O
O
F
• Standard deviation of the residual noise
• Noise components are due to the coarseness of the fake
finger surface
Texture-based Features
22
• First order statistics
Uniformity of grey
levels is less in
live
Perspiration-based Features
23
• Individual pore spacing
1. Image transformed into the ridge signal
2. Analysis in the Fourier domain
3. Total energy associated to the frequencies
corresponding to the spatial frequencies of pores
High
resolution
sensor
1000 dpi
• Intensity-based
• Spoofs are distributed in the dark
• Grey Level (GL) Ratio:
# of pixels with GL in (150, 253)/(1,149)
Data details
24
DATA SET LivDet13
Dataset Scanner
Live Training
Samples
Live Training
Fingers
Live Testing
Samples
Live Testing
Fingers
1 Biometrika 1000 200 1000 200
2 Italdata 1000 200 1000 200
DATA SET LivDet13
Dataset Scanner
Spoof Training
Samples
Spoof Training
Fingers
Spoof Testing
Samples
Spoof Testing
Fingers
1 Biometrika 1000 100 1000 100
2 Italdata 1000 100 1000 100
Classification Results
25
• Texture-based
• First order statistics
• Second order statistics
• Power spectrum analysis
• Local Binary Pattern
• Weber Local Descriptor
• Perspiration-based
• Intensity-based
• Quality-based
• Pores-based
Marasco and Sansone 2012 [1]
• FLR=12.6%; FSA=12.3%
LivDet09 databases
• FLR=11.61; FSA=6.2%
LivDet11 Digital Persona
• FLR=11.61; FSA=6.2%
LivDet13
Marasco and Sansone [1] combined
with Gragnaniello et al. [2]
• FLR=11.3; FSA=1.8%
LivDet13 Biometrika
• FLR=4.9; FSA=2.1%
LivDet13 Italdata
[1] E. Marasco and C. Sansone. Combining perspiration- and morphology-based static features for fingerprint liveness detection.
Pattern Recognition Letters, 33:1148–1156, 2012
[2] C. Sansone D. Gragnaniello, G. Poggi and L. Verdoliva. Fingerprint liveness detection based on weber local image descriptor.
IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BioMs), pages 1–5, 2013
BBN-based to fuse liveness with
match scores
26
BBN: Bayesian Belief Network
• The liveness measure is assumed to influence match scores
• The joint probability is based on the topology of the network:
• IIII identity state
• SSSSgggg liveness state of gallery
• SSSSpppp liveness state of probe
Events:
P(I)P(Sg)P(Sp)Sg)|P(lgSp)|P(lpI)lp,lg,|P(m
Sg)Sp,I,lg,lp,P(m, =
Bayesian Inference
27
From previous slide
The probability of identity state is based
on both match scores and liveness values
Target: given liveness and match scores, what is the probability
that both probe and gallery samples pertain to the same identity
and both are live samples?
lg)lp,P(m,
Sg)Sp,I,lg,lp,P(m,
lg)lp,m,|SgSp,P(I, =
lg)lg)P(lp,lp,|P(m
Sg)P(I)Sg)P(Sp)P(|Sp)P(lg|I)P(lplp,lg,|P(m
=
lp)lg,|P(m
I)lp,lg,|P(I)P(m
P(lg)
Sg)P(Sg)|P(lg
P(lp)
Sp)P(Sp)|P(lp
=
lp)lg,|P(m
lp)lg,|lg)P(mlp,m,|P(I
lg)|Sg(P)lp|Sp(P=
lp)lg,m,|P(Ilg)|Sg(P)lp|Sp(P=
Independence between
andlg lp
)lplg,|I(P)I(P =
28
Results (Silicone, training rate 50%)
Method Verification
FMR% FNMR%
Spoof Detection
FSAR% FLRR%
Global
GFAR% GFRR%
4 (FB) 0.103 5.044 5.244 12.516 0.308 14.217
4 (NN) 0.002 5.187 5.297 12.558 0.241 15.696
• Method 1 achieves best spoof detection performance with a less
accurate liveness detector
Method Verification
FMR% FNMR%
Spoof Detection
FSAR% FLRR%
Global
GFAR% GFRR%
4 (FB) 0.089 15.866 0.316 12.434 0.046 4.195
4 (NN) 0.011 16.415 0.320 12.475 0.008 4.634
Results (Gelatin, training rate 50%)
• The lowest global error rates are achieved with gelatin, where
the liveness measure is accurate
Open Issues
29
• Testing in the presence of unknown spoof materials
• Learning-based
• Certification
• Integration with the matcher
• Performance metrics
Questions?
30

Weitere ähnliche Inhalte

Was ist angesagt?

Biometric Technology
Biometric TechnologyBiometric Technology
Biometric TechnologyAdoitya Kaila
 
introducción a Machine Learning
introducción a Machine Learningintroducción a Machine Learning
introducción a Machine Learningbutest
 
CNIT 140: Perimeter Security
CNIT 140: Perimeter SecurityCNIT 140: Perimeter Security
CNIT 140: Perimeter SecuritySam Bowne
 
Vehicle monitoring and surveillance
Vehicle monitoring and surveillanceVehicle monitoring and surveillance
Vehicle monitoring and surveillancejiju7172
 
Fingerprint Technology
Fingerprint TechnologyFingerprint Technology
Fingerprint TechnologyJoy Dutta
 
CIS14: Physical and Logical Access Control Convergence
CIS14: Physical and Logical Access Control ConvergenceCIS14: Physical and Logical Access Control Convergence
CIS14: Physical and Logical Access Control ConvergenceCloudIDSummit
 
Face detection and recognition report with pi in single poster
Face detection and recognition report with pi in single posterFace detection and recognition report with pi in single poster
Face detection and recognition report with pi in single posterhetvi naik
 
Biometrics & AI (Artificial Intelligence) is the future of Authentication
Biometrics & AI (Artificial Intelligence) is the future of AuthenticationBiometrics & AI (Artificial Intelligence) is the future of Authentication
Biometrics & AI (Artificial Intelligence) is the future of AuthenticationTony Chew
 
Supervised Machine Learning in R
Supervised  Machine Learning  in RSupervised  Machine Learning  in R
Supervised Machine Learning in RBabu Priyavrat
 
Pattern recognition 3d face recognition
Pattern recognition 3d face recognitionPattern recognition 3d face recognition
Pattern recognition 3d face recognitionMazin Alwaaly
 
Biometrics/fingerprint sensors
Biometrics/fingerprint sensorsBiometrics/fingerprint sensors
Biometrics/fingerprint sensorsJeffrey Funk
 

Was ist angesagt? (20)

Fingerprint Based Biometric ATM Authentication System
Fingerprint Based Biometric ATM Authentication SystemFingerprint Based Biometric ATM Authentication System
Fingerprint Based Biometric ATM Authentication System
 
Biometric Technology
Biometric TechnologyBiometric Technology
Biometric Technology
 
introducción a Machine Learning
introducción a Machine Learningintroducción a Machine Learning
introducción a Machine Learning
 
Smart helmet
Smart helmetSmart helmet
Smart helmet
 
CNIT 140: Perimeter Security
CNIT 140: Perimeter SecurityCNIT 140: Perimeter Security
CNIT 140: Perimeter Security
 
Cyber forensics
Cyber forensicsCyber forensics
Cyber forensics
 
Mobile Forensics
Mobile Forensics Mobile Forensics
Mobile Forensics
 
Vehicle monitoring and surveillance
Vehicle monitoring and surveillanceVehicle monitoring and surveillance
Vehicle monitoring and surveillance
 
Fingerprint Technology
Fingerprint TechnologyFingerprint Technology
Fingerprint Technology
 
CIS14: Physical and Logical Access Control Convergence
CIS14: Physical and Logical Access Control ConvergenceCIS14: Physical and Logical Access Control Convergence
CIS14: Physical and Logical Access Control Convergence
 
The Basics of Cyber Insurance
The Basics of Cyber InsuranceThe Basics of Cyber Insurance
The Basics of Cyber Insurance
 
Face detection and recognition report with pi in single poster
Face detection and recognition report with pi in single posterFace detection and recognition report with pi in single poster
Face detection and recognition report with pi in single poster
 
Biometrics
BiometricsBiometrics
Biometrics
 
CS6004 Cyber Forensics
CS6004 Cyber ForensicsCS6004 Cyber Forensics
CS6004 Cyber Forensics
 
Machine Learning ppt
Machine Learning pptMachine Learning ppt
Machine Learning ppt
 
Biometrics & AI (Artificial Intelligence) is the future of Authentication
Biometrics & AI (Artificial Intelligence) is the future of AuthenticationBiometrics & AI (Artificial Intelligence) is the future of Authentication
Biometrics & AI (Artificial Intelligence) is the future of Authentication
 
Supervised Machine Learning in R
Supervised  Machine Learning  in RSupervised  Machine Learning  in R
Supervised Machine Learning in R
 
Pattern recognition 3d face recognition
Pattern recognition 3d face recognitionPattern recognition 3d face recognition
Pattern recognition 3d face recognition
 
Voice recognition
Voice recognitionVoice recognition
Voice recognition
 
Biometrics/fingerprint sensors
Biometrics/fingerprint sensorsBiometrics/fingerprint sensors
Biometrics/fingerprint sensors
 

Andere mochten auch

Galina Lavrentyeva - Anti-spoofing Methods for Automatic Speaker Verification...
Galina Lavrentyeva - Anti-spoofing Methods for Automatic Speaker Verification...Galina Lavrentyeva - Anti-spoofing Methods for Automatic Speaker Verification...
Galina Lavrentyeva - Anti-spoofing Methods for Automatic Speaker Verification...AIST
 
GPS[Global Positioning System]
GPS[Global Positioning System]GPS[Global Positioning System]
GPS[Global Positioning System]Ishwar Bulbule
 
Biometrics and its hacking
Biometrics and its hackingBiometrics and its hacking
Biometrics and its hackingNeel Parikh
 
Research in Liveness Detection - Martin Drahanský
Research in Liveness Detection - Martin DrahanskýResearch in Liveness Detection - Martin Drahanský
Research in Liveness Detection - Martin DrahanskýSecurity Session
 
Face spoofing detection using texture analysis
Face spoofing detection  using texture analysisFace spoofing detection  using texture analysis
Face spoofing detection using texture analysisSREEKUTTY SREEKUMAR
 
Face recognition ppt
Face recognition pptFace recognition ppt
Face recognition pptSantosh Kumar
 

Andere mochten auch (10)

Galina Lavrentyeva - Anti-spoofing Methods for Automatic Speaker Verification...
Galina Lavrentyeva - Anti-spoofing Methods for Automatic Speaker Verification...Galina Lavrentyeva - Anti-spoofing Methods for Automatic Speaker Verification...
Galina Lavrentyeva - Anti-spoofing Methods for Automatic Speaker Verification...
 
GPS Signals (1)
GPS Signals (1)GPS Signals (1)
GPS Signals (1)
 
GPS[Global Positioning System]
GPS[Global Positioning System]GPS[Global Positioning System]
GPS[Global Positioning System]
 
Biometrics and its hacking
Biometrics and its hackingBiometrics and its hacking
Biometrics and its hacking
 
Research in Liveness Detection - Martin Drahanský
Research in Liveness Detection - Martin DrahanskýResearch in Liveness Detection - Martin Drahanský
Research in Liveness Detection - Martin Drahanský
 
Fingerprint recognition
Fingerprint recognitionFingerprint recognition
Fingerprint recognition
 
Face spoofing detection using texture analysis
Face spoofing detection  using texture analysisFace spoofing detection  using texture analysis
Face spoofing detection using texture analysis
 
Gps signal structure
Gps signal structureGps signal structure
Gps signal structure
 
Face recognition ppt
Face recognition pptFace recognition ppt
Face recognition ppt
 
GPS ppt.
GPS ppt. GPS ppt.
GPS ppt.
 

Ähnlich wie Fingerprint Anti-Spoofing [ Talk in Stanford Nov. 2013]

Slide-show on Biometrics
Slide-show on BiometricsSlide-show on Biometrics
Slide-show on BiometricsPathik504
 
Fingerprint Analaysis
Fingerprint AnalaysisFingerprint Analaysis
Fingerprint AnalaysisANIKLAL2
 
Biometric Class Attendace System
Biometric Class Attendace SystemBiometric Class Attendace System
Biometric Class Attendace SystemAgbona Azeez
 
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative...
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative...A Deep Neural Framework for Continuous Sign Language Recognition by Iterative...
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative...ijtsrd
 
Fingerprint recognition (term paper) Project
Fingerprint recognition (term paper) Project Fingerprint recognition (term paper) Project
Fingerprint recognition (term paper) Project Abhishek Walia
 
Biometrics Authentication of Fingerprint with Using Fingerprint Reader and Mi...
Biometrics Authentication of Fingerprint with Using Fingerprint Reader and Mi...Biometrics Authentication of Fingerprint with Using Fingerprint Reader and Mi...
Biometrics Authentication of Fingerprint with Using Fingerprint Reader and Mi...TELKOMNIKA JOURNAL
 
novel method of identifying fingerprint using minutiae matching in biometric ...
novel method of identifying fingerprint using minutiae matching in biometric ...novel method of identifying fingerprint using minutiae matching in biometric ...
novel method of identifying fingerprint using minutiae matching in biometric ...INFOGAIN PUBLICATION
 
Comparison of various Biometric methods
Comparison of various Biometric methodsComparison of various Biometric methods
Comparison of various Biometric methodsRupinder Saini
 
Report on Finger print sensor and its application
Report on Finger print sensor and its applicationReport on Finger print sensor and its application
Report on Finger print sensor and its applicationArnab Podder
 
Pre-Processing Image Algorithm for Fingerprint Recognition and its Implementa...
Pre-Processing Image Algorithm for Fingerprint Recognition and its Implementa...Pre-Processing Image Algorithm for Fingerprint Recognition and its Implementa...
Pre-Processing Image Algorithm for Fingerprint Recognition and its Implementa...ijseajournal
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)IJERD Editor
 
FUSION OF GAIT AND FINGERPRINT FOR USER AUTHENTICATION ON MOBILE DEVICES
FUSION OF GAIT AND FINGERPRINT FOR USER AUTHENTICATION ON MOBILE DEVICESFUSION OF GAIT AND FINGERPRINT FOR USER AUTHENTICATION ON MOBILE DEVICES
FUSION OF GAIT AND FINGERPRINT FOR USER AUTHENTICATION ON MOBILE DEVICESvasim hasina
 
Sum Rule Based Matching Score Level Fusion of Fingerprint and Iris Images for...
Sum Rule Based Matching Score Level Fusion of Fingerprint and Iris Images for...Sum Rule Based Matching Score Level Fusion of Fingerprint and Iris Images for...
Sum Rule Based Matching Score Level Fusion of Fingerprint and Iris Images for...IRJET Journal
 
MDD Project Report By Dharmendra singh [Srm University] Ncr Delhi
MDD Project Report By Dharmendra singh [Srm University] Ncr DelhiMDD Project Report By Dharmendra singh [Srm University] Ncr Delhi
MDD Project Report By Dharmendra singh [Srm University] Ncr DelhiDharmendrasingh417
 

Ähnlich wie Fingerprint Anti-Spoofing [ Talk in Stanford Nov. 2013] (20)

Slide-show on Biometrics
Slide-show on BiometricsSlide-show on Biometrics
Slide-show on Biometrics
 
Fingerprint Analaysis
Fingerprint AnalaysisFingerprint Analaysis
Fingerprint Analaysis
 
Biometric Class Attendace System
Biometric Class Attendace SystemBiometric Class Attendace System
Biometric Class Attendace System
 
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative...
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative...A Deep Neural Framework for Continuous Sign Language Recognition by Iterative...
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative...
 
E0364024030
E0364024030E0364024030
E0364024030
 
Fingerprint recognition (term paper) Project
Fingerprint recognition (term paper) Project Fingerprint recognition (term paper) Project
Fingerprint recognition (term paper) Project
 
Biometrics Authentication of Fingerprint with Using Fingerprint Reader and Mi...
Biometrics Authentication of Fingerprint with Using Fingerprint Reader and Mi...Biometrics Authentication of Fingerprint with Using Fingerprint Reader and Mi...
Biometrics Authentication of Fingerprint with Using Fingerprint Reader and Mi...
 
novel method of identifying fingerprint using minutiae matching in biometric ...
novel method of identifying fingerprint using minutiae matching in biometric ...novel method of identifying fingerprint using minutiae matching in biometric ...
novel method of identifying fingerprint using minutiae matching in biometric ...
 
Finger Print Sensor
Finger Print SensorFinger Print Sensor
Finger Print Sensor
 
Comparison of various Biometric methods
Comparison of various Biometric methodsComparison of various Biometric methods
Comparison of various Biometric methods
 
Report on Finger print sensor and its application
Report on Finger print sensor and its applicationReport on Finger print sensor and its application
Report on Finger print sensor and its application
 
Pre-Processing Image Algorithm for Fingerprint Recognition and its Implementa...
Pre-Processing Image Algorithm for Fingerprint Recognition and its Implementa...Pre-Processing Image Algorithm for Fingerprint Recognition and its Implementa...
Pre-Processing Image Algorithm for Fingerprint Recognition and its Implementa...
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 
L026070074
L026070074L026070074
L026070074
 
Ijetcas14 598
Ijetcas14 598Ijetcas14 598
Ijetcas14 598
 
Biometrics poster
Biometrics posterBiometrics poster
Biometrics poster
 
FUSION OF GAIT AND FINGERPRINT FOR USER AUTHENTICATION ON MOBILE DEVICES
FUSION OF GAIT AND FINGERPRINT FOR USER AUTHENTICATION ON MOBILE DEVICESFUSION OF GAIT AND FINGERPRINT FOR USER AUTHENTICATION ON MOBILE DEVICES
FUSION OF GAIT AND FINGERPRINT FOR USER AUTHENTICATION ON MOBILE DEVICES
 
Sum Rule Based Matching Score Level Fusion of Fingerprint and Iris Images for...
Sum Rule Based Matching Score Level Fusion of Fingerprint and Iris Images for...Sum Rule Based Matching Score Level Fusion of Fingerprint and Iris Images for...
Sum Rule Based Matching Score Level Fusion of Fingerprint and Iris Images for...
 
Poster on biometrics
Poster on biometricsPoster on biometrics
Poster on biometrics
 
MDD Project Report By Dharmendra singh [Srm University] Ncr Delhi
MDD Project Report By Dharmendra singh [Srm University] Ncr DelhiMDD Project Report By Dharmendra singh [Srm University] Ncr Delhi
MDD Project Report By Dharmendra singh [Srm University] Ncr Delhi
 

Kürzlich hochgeladen

Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxOrlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxMuhammadAsimMuhammad6
 
Moment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilMoment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilVinayVitekari
 
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxHOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxSCMS School of Architecture
 
Computer Networks Basics of Network Devices
Computer Networks  Basics of Network DevicesComputer Networks  Basics of Network Devices
Computer Networks Basics of Network DevicesChandrakantDivate1
 
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptxA CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptxmaisarahman1
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfJiananWang21
 
Hospital management system project report.pdf
Hospital management system project report.pdfHospital management system project report.pdf
Hospital management system project report.pdfKamal Acharya
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . pptDineshKumar4165
 
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdfAldoGarca30
 
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptxS1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptxSCMS School of Architecture
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptxJIT KUMAR GUPTA
 
"Lesotho Leaps Forward: A Chronicle of Transformative Developments"
"Lesotho Leaps Forward: A Chronicle of Transformative Developments""Lesotho Leaps Forward: A Chronicle of Transformative Developments"
"Lesotho Leaps Forward: A Chronicle of Transformative Developments"mphochane1998
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Arindam Chakraborty, Ph.D., P.E. (CA, TX)
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxJuliansyahHarahap1
 
Wadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptxWadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptxNadaHaitham1
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXssuser89054b
 
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startQuintin Balsdon
 
Engineering Drawing focus on projection of planes
Engineering Drawing focus on projection of planesEngineering Drawing focus on projection of planes
Engineering Drawing focus on projection of planesRAJNEESHKUMAR341697
 

Kürzlich hochgeladen (20)

Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxOrlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
 
Moment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilMoment Distribution Method For Btech Civil
Moment Distribution Method For Btech Civil
 
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxHOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
 
Computer Networks Basics of Network Devices
Computer Networks  Basics of Network DevicesComputer Networks  Basics of Network Devices
Computer Networks Basics of Network Devices
 
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptxA CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdf
 
Hospital management system project report.pdf
Hospital management system project report.pdfHospital management system project report.pdf
Hospital management system project report.pdf
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
 
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
 
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced LoadsFEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
 
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptxS1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
 
"Lesotho Leaps Forward: A Chronicle of Transformative Developments"
"Lesotho Leaps Forward: A Chronicle of Transformative Developments""Lesotho Leaps Forward: A Chronicle of Transformative Developments"
"Lesotho Leaps Forward: A Chronicle of Transformative Developments"
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptx
 
Wadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptxWadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptx
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the start
 
Engineering Drawing focus on projection of planes
Engineering Drawing focus on projection of planesEngineering Drawing focus on projection of planes
Engineering Drawing focus on projection of planes
 
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
 

Fingerprint Anti-Spoofing [ Talk in Stanford Nov. 2013]

  • 1. Anti-Spoofing Algorithms for Fingerprint Systems Emanuela Marasco 12 Lane Department of Computer Science and Electrical Engineering
  • 2. Security of Fingerprint Systems 13 [1] http://nexidbiometrics.com/brazilian-doctor-arrested-for-using-fake-fingerprints/ [2] http://secureidnews.com/news-item/apples-touch-id-spoofed/ • What about Impersonation? • March 2013, Brazilian doctor accused to use spoof fingerprints to check-in co-workers not present at work place • September 2013, the iPhone5S equipped with Touch ID sensor accepted a spoof fingerprint as live Police recovered six silicone fingers After two days only it was released
  • 3. Fingerprint Spoofing • Liveness detection distinguishes live human biometric presentations from spoof artifacts [2],[3],[4] • The liveness of a fingerprint is assessed by a numerical entity 14 [1] T. Matsumoto, H. Matsumoto, K. Yamada, and S. Hoshino. Impact of artificial gummy fingers on fingerprint systems. Optical Security and Counterfeit Deterrence Techniques IV, 4677:275–289, January 2002. [2] S. Schuckers. Spoofing and anti-spoofing measures. Information Security Technical Report, 7(4):56–62, 2002. Making artificial fingerprints directly from a live finger [1] • Fingerprint systems are vulnerable to spoof presentations [1] [3] D. Yambay, L. Ghiani, P. Denti, G. Marcialis, F. Roli and S. Schuckers. LivDet 2011 – Fingerprint Liveness Detection Competition 2011. The 5th International Conference on Biometrics (ICB), pages 208-215, March 2012. [4] G. Marcialis, A. Lewicke, B. Tan, P. Coli, D. Grimberg, A. Congiu, A. Tidu, F. Roli, and S. Schuckers. First international fingerprint liveness detection competition (LivDet09). The 15th International Conference on Image Analysis and Processing (ICIAP), pages 12–23, September 2009.
  • 4. The considered dangerous scenarios 15 http://www2.washjeff.edu/users/ahollandminkley/Biometric/index.htmlThe images are taken from • A person enrolls using a live finger • A spoof artifact of the true finger is used during verification [1] live spoof Enrollment Verification [1] S. Schuckers. Spoofing and anti-spoofing measures. Information Security Technical Report, 7(4):56–62, 2002.
  • 5. Live or Spoof? 16 Images taken from LivDet09
  • 6. Vulnerability Degree vs. Fingerprint Sensing 17 • Optical sensors: light entering the prism is reflected at valleys and absorbed at the ridges • Physiological vulnerability: materials with light reflectivity similar to that of the skin • Device: differences in ergonomics, arrangement of elements • Capacitive sensors: the finger is modeled as the upper electrode of a capacitor • Fingerprint in gelatin are more dangerous Spoof fingerprints obtained using the same material (silicone) but scanned by two different optical devices (CrossMatch and Biometrika from LivDet09
  • 7. How to make Fingerprint Spoof? 18 • Materials which can be scanned (e.g., play-doh, gelatin, …) [1] S. Schuckers. Spoofing and anti-spoofing measures. Information Security Technical Report, 7(4):56–62, 2002.
  • 10. Texture-based Features 21 Original Image De-noised Image Residual Noise Original Image De-noised Image Residual Noise L I V E S P O O F • Standard deviation of the residual noise • Noise components are due to the coarseness of the fake finger surface
  • 11. Texture-based Features 22 • First order statistics Uniformity of grey levels is less in live
  • 12. Perspiration-based Features 23 • Individual pore spacing 1. Image transformed into the ridge signal 2. Analysis in the Fourier domain 3. Total energy associated to the frequencies corresponding to the spatial frequencies of pores High resolution sensor 1000 dpi • Intensity-based • Spoofs are distributed in the dark • Grey Level (GL) Ratio: # of pixels with GL in (150, 253)/(1,149)
  • 13. Data details 24 DATA SET LivDet13 Dataset Scanner Live Training Samples Live Training Fingers Live Testing Samples Live Testing Fingers 1 Biometrika 1000 200 1000 200 2 Italdata 1000 200 1000 200 DATA SET LivDet13 Dataset Scanner Spoof Training Samples Spoof Training Fingers Spoof Testing Samples Spoof Testing Fingers 1 Biometrika 1000 100 1000 100 2 Italdata 1000 100 1000 100
  • 14. Classification Results 25 • Texture-based • First order statistics • Second order statistics • Power spectrum analysis • Local Binary Pattern • Weber Local Descriptor • Perspiration-based • Intensity-based • Quality-based • Pores-based Marasco and Sansone 2012 [1] • FLR=12.6%; FSA=12.3% LivDet09 databases • FLR=11.61; FSA=6.2% LivDet11 Digital Persona • FLR=11.61; FSA=6.2% LivDet13 Marasco and Sansone [1] combined with Gragnaniello et al. [2] • FLR=11.3; FSA=1.8% LivDet13 Biometrika • FLR=4.9; FSA=2.1% LivDet13 Italdata [1] E. Marasco and C. Sansone. Combining perspiration- and morphology-based static features for fingerprint liveness detection. Pattern Recognition Letters, 33:1148–1156, 2012 [2] C. Sansone D. Gragnaniello, G. Poggi and L. Verdoliva. Fingerprint liveness detection based on weber local image descriptor. IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BioMs), pages 1–5, 2013
  • 15. BBN-based to fuse liveness with match scores 26 BBN: Bayesian Belief Network • The liveness measure is assumed to influence match scores • The joint probability is based on the topology of the network: • IIII identity state • SSSSgggg liveness state of gallery • SSSSpppp liveness state of probe Events: P(I)P(Sg)P(Sp)Sg)|P(lgSp)|P(lpI)lp,lg,|P(m Sg)Sp,I,lg,lp,P(m, =
  • 16. Bayesian Inference 27 From previous slide The probability of identity state is based on both match scores and liveness values Target: given liveness and match scores, what is the probability that both probe and gallery samples pertain to the same identity and both are live samples? lg)lp,P(m, Sg)Sp,I,lg,lp,P(m, lg)lp,m,|SgSp,P(I, = lg)lg)P(lp,lp,|P(m Sg)P(I)Sg)P(Sp)P(|Sp)P(lg|I)P(lplp,lg,|P(m = lp)lg,|P(m I)lp,lg,|P(I)P(m P(lg) Sg)P(Sg)|P(lg P(lp) Sp)P(Sp)|P(lp = lp)lg,|P(m lp)lg,|lg)P(mlp,m,|P(I lg)|Sg(P)lp|Sp(P= lp)lg,m,|P(Ilg)|Sg(P)lp|Sp(P= Independence between andlg lp )lplg,|I(P)I(P =
  • 17. 28 Results (Silicone, training rate 50%) Method Verification FMR% FNMR% Spoof Detection FSAR% FLRR% Global GFAR% GFRR% 4 (FB) 0.103 5.044 5.244 12.516 0.308 14.217 4 (NN) 0.002 5.187 5.297 12.558 0.241 15.696 • Method 1 achieves best spoof detection performance with a less accurate liveness detector Method Verification FMR% FNMR% Spoof Detection FSAR% FLRR% Global GFAR% GFRR% 4 (FB) 0.089 15.866 0.316 12.434 0.046 4.195 4 (NN) 0.011 16.415 0.320 12.475 0.008 4.634 Results (Gelatin, training rate 50%) • The lowest global error rates are achieved with gelatin, where the liveness measure is accurate
  • 18. Open Issues 29 • Testing in the presence of unknown spoof materials • Learning-based • Certification • Integration with the matcher • Performance metrics