SlideShare una empresa de Scribd logo
1 de 1
Descargar para leer sin conexión
Fusion of multiple clues for photo-attack detection in face
                    recognition systems
Roberto Tronci , Daniele Muntoni , Gianluca Fadda , Maurizio Pili , Nicola Sirena , Marco Ristori ,
                      1,2                                    1,2                                                      1                         1                          1                         1


                                Gabriele Murgia , Fabio Roli
                                               1             2


                                  1
                                   Ambient Intelligence Lab, Sardinia DistrICT, Sardegna Ricerche, ITALY
                            2
                                DIEE, Dept. Electric and Electronic Engineering, University of Cagliari, ITALY
         {roberto.tronci, muntoni, fadda, maurizio.pili, sirena, gabriele.murgia, ristori}@sardegnaricerche.it
                                 {roberto.tronci, daniele.muntoni, roli}diee.unica.it


                                   Introduction
              SARDEGNA
              RICERCHE             We faced the problem of detecting 2-D face spoofing attacks performed by
                                   placing a printed photo of a real user in front of the camera.
                                   For this type of attack it is not possible to relay just on the face
                                   movements as a clue of vitality because the attacker can easily simulate
                                                                                                                                                                    IJCB2011
                                   such a case, and also because real users often show a “low vitality” during
                                   the authentication session.
                                   In this paper, we perform both video and static analysis in order to employ
                                   complementary information about motion, texture and liveness and
                                   consequently to obtain a more robust classification.


Our approach                                                                                                     Classification
AmILab's Spoof Detector implements a multi-clue approach.                                                       At classification stage scores are computed over a sliding window of a few
                                                                                                                seconds of video.
Static analysis tackles the visual characteristics of a photo attack.                                           Within this window, static analysis results in FxN scores (F frames and N
The visual representations that we propose to use are: Color and Edge                                           visual representations). A unique score is computed through a DSC
Directivity Descriptor, Fuzzy Color and Texture Histogram, MPEG-7                                               algorithm. :
Descriptors (like Scalable Color and Edge Histogram), Gabor Texture,                                                        S sa = 1− ⋅min { S i , f }⋅max { S i , f } i∈[1, N ] , f ∈[1, F ]
Tamura Texture, RGB and HSV Histograms, and JPEG Histogram.
For each frame, each of the above mentioned visual representations result                                       Finally, fusion between static and video analysis is performed as:
in a specific score.


Video analysis aims to detect vitality clues. Clues examined in this work
are motion analysis of the scene and the number of eye blinks that are
                                                                                                                                     S =
                                                                                                                                            {   ⋅S sa1 −  ⋅S bl ,
                                                                                                                                                 1⋅S sa  2⋅S bl  3⋅S m ,
                                                                                                                                                                                if S m is high
                                                                                                                                                                                if S m is low
represented by two independent scores.
                                                                                                                             S sa
                                                                                      Still Frame Characteristic analysis




                                                                                                                                                       D    S
                                                                                                                                                       S
                                                                                                                             S bl                      C
                                                                                               Blink detection




                                                                                                                            Sm          LOW?
                                                                                                Global motion                                    Yes




Experimental results: the face spoof competition
For our experiments we used the Print-Attack Replay Database developed
for the IJCB 2011 Competition on counter measures to 2D facial spoofing
attacks from the Idiap Research Institute.
Although static analysis alone easily achieves a perfect separation in
the test set, we enhanced its classification with the video analysis in
order to grant performances even with higher quality printed photos or
high quality displays (smart-phones, tablets and other modern portable¿

devices).                                                             ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                                      ¿
                                                       −¿= f k  x i  omega −¿ ,
                                                                      i
                                                                      s¿
                                                                       ik
                                                                   −¿=¿
                                                      ¿= f k  x i  omega¿ , S ¿
                                                                                  k
                                                                  i
                                                                  s¿
                                                                   ik
                                                                 ¿=¿
                                                                  S ¿k




                                                                                                                 Introduction of video analysis results in lower performances in terms of
                                                                                                                 separation of scores' distributions. However, the proposed fusion scheme
                                                                                                                 still proved to be very effective and robust.
                                                                                                                 The contribution of video analysis in terms of robust classification will be
                                                                                                                 further investigated in future works.




Contacts

                         Ambient Intelligence Lab - Edificio 1, Loc. Piscinamanna, 09010 Pula (CA), Italy - Tel. +39 070 9243 2682
                                              http://prag.diee.unica.it/amilab/ labiam@sardegnaricerche.it

Más contenido relacionado

Más de Pluribus One

Battista Biggio, Invited Keynote @ AISec 2014 - On Learning and Recognition o...
Battista Biggio, Invited Keynote @ AISec 2014 - On Learning and Recognition o...Battista Biggio, Invited Keynote @ AISec 2014 - On Learning and Recognition o...
Battista Biggio, Invited Keynote @ AISec 2014 - On Learning and Recognition o...
Pluribus One
 
Battista Biggio @ S+SSPR2014, Joensuu, Finland -- Poisoning Complete-Linkage ...
Battista Biggio @ S+SSPR2014, Joensuu, Finland -- Poisoning Complete-Linkage ...Battista Biggio @ S+SSPR2014, Joensuu, Finland -- Poisoning Complete-Linkage ...
Battista Biggio @ S+SSPR2014, Joensuu, Finland -- Poisoning Complete-Linkage ...
Pluribus One
 
Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning a...
Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning a...Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning a...
Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning a...
Pluribus One
 
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Pluribus One
 
Zahid Akhtar - Ph.D. Defense Slides
Zahid Akhtar - Ph.D. Defense SlidesZahid Akhtar - Ph.D. Defense Slides
Zahid Akhtar - Ph.D. Defense Slides
Pluribus One
 
Design of robust classifiers for adversarial environments - Systems, Man, and...
Design of robust classifiers for adversarial environments - Systems, Man, and...Design of robust classifiers for adversarial environments - Systems, Man, and...
Design of robust classifiers for adversarial environments - Systems, Man, and...
Pluribus One
 
Robustness of multimodal biometric verification systems under realistic spoof...
Robustness of multimodal biometric verification systems under realistic spoof...Robustness of multimodal biometric verification systems under realistic spoof...
Robustness of multimodal biometric verification systems under realistic spoof...
Pluribus One
 
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Pluribus One
 

Más de Pluribus One (20)

Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
 
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
 
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
 
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
 
On Security and Sparsity of Linear Classifiers for Adversarial Settings
On Security and Sparsity of Linear Classifiers for Adversarial SettingsOn Security and Sparsity of Linear Classifiers for Adversarial Settings
On Security and Sparsity of Linear Classifiers for Adversarial Settings
 
Secure Kernel Machines against Evasion Attacks
Secure Kernel Machines against Evasion AttacksSecure Kernel Machines against Evasion Attacks
Secure Kernel Machines against Evasion Attacks
 
Machine Learning under Attack: Vulnerability Exploitation and Security Measures
Machine Learning under Attack: Vulnerability Exploitation and Security MeasuresMachine Learning under Attack: Vulnerability Exploitation and Security Measures
Machine Learning under Attack: Vulnerability Exploitation and Security Measures
 
Battista Biggio @ ICML 2015 - "Is Feature Selection Secure against Training D...
Battista Biggio @ ICML 2015 - "Is Feature Selection Secure against Training D...Battista Biggio @ ICML 2015 - "Is Feature Selection Secure against Training D...
Battista Biggio @ ICML 2015 - "Is Feature Selection Secure against Training D...
 
Battista Biggio @ MCS 2015, June 29 - July 1, Guenzburg, Germany: "1.5-class ...
Battista Biggio @ MCS 2015, June 29 - July 1, Guenzburg, Germany: "1.5-class ...Battista Biggio @ MCS 2015, June 29 - July 1, Guenzburg, Germany: "1.5-class ...
Battista Biggio @ MCS 2015, June 29 - July 1, Guenzburg, Germany: "1.5-class ...
 
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
 
Battista Biggio, Invited Keynote @ AISec 2014 - On Learning and Recognition o...
Battista Biggio, Invited Keynote @ AISec 2014 - On Learning and Recognition o...Battista Biggio, Invited Keynote @ AISec 2014 - On Learning and Recognition o...
Battista Biggio, Invited Keynote @ AISec 2014 - On Learning and Recognition o...
 
Battista Biggio @ AISec 2014 - Poisoning Behavioral Malware Clustering
Battista Biggio @ AISec 2014 - Poisoning Behavioral Malware ClusteringBattista Biggio @ AISec 2014 - Poisoning Behavioral Malware Clustering
Battista Biggio @ AISec 2014 - Poisoning Behavioral Malware Clustering
 
Battista Biggio @ S+SSPR2014, Joensuu, Finland -- Poisoning Complete-Linkage ...
Battista Biggio @ S+SSPR2014, Joensuu, Finland -- Poisoning Complete-Linkage ...Battista Biggio @ S+SSPR2014, Joensuu, Finland -- Poisoning Complete-Linkage ...
Battista Biggio @ S+SSPR2014, Joensuu, Finland -- Poisoning Complete-Linkage ...
 
Battista Biggio @ AISec 2013 - Is Data Clustering in Adversarial Settings Sec...
Battista Biggio @ AISec 2013 - Is Data Clustering in Adversarial Settings Sec...Battista Biggio @ AISec 2013 - Is Data Clustering in Adversarial Settings Sec...
Battista Biggio @ AISec 2013 - Is Data Clustering in Adversarial Settings Sec...
 
Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning a...
Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning a...Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning a...
Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning a...
 
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
 
Zahid Akhtar - Ph.D. Defense Slides
Zahid Akhtar - Ph.D. Defense SlidesZahid Akhtar - Ph.D. Defense Slides
Zahid Akhtar - Ph.D. Defense Slides
 
Design of robust classifiers for adversarial environments - Systems, Man, and...
Design of robust classifiers for adversarial environments - Systems, Man, and...Design of robust classifiers for adversarial environments - Systems, Man, and...
Design of robust classifiers for adversarial environments - Systems, Man, and...
 
Robustness of multimodal biometric verification systems under realistic spoof...
Robustness of multimodal biometric verification systems under realistic spoof...Robustness of multimodal biometric verification systems under realistic spoof...
Robustness of multimodal biometric verification systems under realistic spoof...
 
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
 

Último

Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Enterprise Knowledge
 

Último (20)

Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 

Amilab IJCB 2011 Poster

  • 1. Fusion of multiple clues for photo-attack detection in face recognition systems Roberto Tronci , Daniele Muntoni , Gianluca Fadda , Maurizio Pili , Nicola Sirena , Marco Ristori , 1,2 1,2 1 1 1 1 Gabriele Murgia , Fabio Roli 1 2 1 Ambient Intelligence Lab, Sardinia DistrICT, Sardegna Ricerche, ITALY 2 DIEE, Dept. Electric and Electronic Engineering, University of Cagliari, ITALY {roberto.tronci, muntoni, fadda, maurizio.pili, sirena, gabriele.murgia, ristori}@sardegnaricerche.it {roberto.tronci, daniele.muntoni, roli}diee.unica.it Introduction SARDEGNA RICERCHE We faced the problem of detecting 2-D face spoofing attacks performed by placing a printed photo of a real user in front of the camera. For this type of attack it is not possible to relay just on the face movements as a clue of vitality because the attacker can easily simulate IJCB2011 such a case, and also because real users often show a “low vitality” during the authentication session. In this paper, we perform both video and static analysis in order to employ complementary information about motion, texture and liveness and consequently to obtain a more robust classification. Our approach Classification AmILab's Spoof Detector implements a multi-clue approach. At classification stage scores are computed over a sliding window of a few seconds of video. Static analysis tackles the visual characteristics of a photo attack. Within this window, static analysis results in FxN scores (F frames and N The visual representations that we propose to use are: Color and Edge visual representations). A unique score is computed through a DSC Directivity Descriptor, Fuzzy Color and Texture Histogram, MPEG-7 algorithm. : Descriptors (like Scalable Color and Edge Histogram), Gabor Texture, S sa = 1− ⋅min { S i , f }⋅max { S i , f } i∈[1, N ] , f ∈[1, F ] Tamura Texture, RGB and HSV Histograms, and JPEG Histogram. For each frame, each of the above mentioned visual representations result Finally, fusion between static and video analysis is performed as: in a specific score. Video analysis aims to detect vitality clues. Clues examined in this work are motion analysis of the scene and the number of eye blinks that are S = { ⋅S sa1 −  ⋅S bl ,  1⋅S sa  2⋅S bl  3⋅S m , if S m is high if S m is low represented by two independent scores. S sa Still Frame Characteristic analysis D S S S bl C Blink detection Sm LOW? Global motion Yes Experimental results: the face spoof competition For our experiments we used the Print-Attack Replay Database developed for the IJCB 2011 Competition on counter measures to 2D facial spoofing attacks from the Idiap Research Institute. Although static analysis alone easily achieves a perfect separation in the test set, we enhanced its classification with the video analysis in order to grant performances even with higher quality printed photos or high quality displays (smart-phones, tablets and other modern portable¿ devices). ¿ ¿ ¿ ¿ ¿ ¿ ¿ ¿ ¿ ¿ ¿ ¿ ¿ −¿= f k  x i  omega −¿ , i s¿ ik −¿=¿ ¿= f k  x i  omega¿ , S ¿ k i s¿ ik ¿=¿ S ¿k Introduction of video analysis results in lower performances in terms of separation of scores' distributions. However, the proposed fusion scheme still proved to be very effective and robust. The contribution of video analysis in terms of robust classification will be further investigated in future works. Contacts Ambient Intelligence Lab - Edificio 1, Loc. Piscinamanna, 09010 Pula (CA), Italy - Tel. +39 070 9243 2682 http://prag.diee.unica.it/amilab/ labiam@sardegnaricerche.it