Deep Composite Face Image Attacks: Generation, Vulnerability and Detection
Face manipulation attacks have drawn the attention of biometric researchers because of their vulnerability to Face Recognition Systems (FRS). This paper proposes a novel scheme to generate Composite Face Image Attacks (CFIA) based on facial attributes using Generative Adversarial Networks (GANs). Gi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10078862/ |
| _version_ | 1797768404965261312 |
|---|---|
| author | Jag Mohan Singh Raghavendra Ramachandra |
| author_facet | Jag Mohan Singh Raghavendra Ramachandra |
| author_sort | Jag Mohan Singh |
| collection | DOAJ |
| description | Face manipulation attacks have drawn the attention of biometric researchers because of their vulnerability to Face Recognition Systems (FRS). This paper proposes a novel scheme to generate Composite Face Image Attacks (CFIA) based on facial attributes using Generative Adversarial Networks (GANs). Given the face images corresponding to two unique data subjects, the proposed CFIA method will independently generate the segmented facial attributes, then blend them using transparent masks to generate the CFIA samples. We generate 526 unique CFIA combinations of facial attributes for each pair of contributory data subjects. Extensive experiments are carried out on our newly generated CFIA dataset consisting of 1000 unique identities with 2000 bona fide samples and 526000 CFIA samples, thus resulting in an overall 528000 face image samples. We present a sequence of experiments to benchmark the attack potential of CFIA samples using four different automatic FRS. We introduced a new metric named Generalized Morphing Attack Potential (G-MAP) to benchmark the vulnerability of generated attacks on FRS effectively. Additional experiments are performed on the representative subset of the CFIA dataset to benchmark both perceptual quality and human observer response. Finally, the CFIA detection performance is benchmarked using three different single image based face Morphing Attack Detection (MAD) algorithms. The source code of the proposed method together with CFIA dataset will be made publicly available: <uri>https://github.com/jagmohaniiit/LatentCompositionCode</uri> |
| first_indexed | 2024-03-12T20:53:50Z |
| format | Article |
| id | doaj.art-5744cd0f198a4a2f8fa05c77e8c2e971 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T20:53:50Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5744cd0f198a4a2f8fa05c77e8c2e9712023-07-31T23:00:23ZengIEEEIEEE Access2169-35362023-01-0111764687648510.1109/ACCESS.2023.326124710078862Deep Composite Face Image Attacks: Generation, Vulnerability and DetectionJag Mohan Singh0https://orcid.org/0000-0002-8901-6791Raghavendra Ramachandra1https://orcid.org/0000-0003-0484-3956Department of Information Security and Communication Technology, Norwegian Biometrics Laboratory, Norwegian University of Science and Technology (NTNU), Gjøvik, NorwayDepartment of Information Security and Communication Technology, Norwegian Biometrics Laboratory, Norwegian University of Science and Technology (NTNU), Gjøvik, NorwayFace manipulation attacks have drawn the attention of biometric researchers because of their vulnerability to Face Recognition Systems (FRS). This paper proposes a novel scheme to generate Composite Face Image Attacks (CFIA) based on facial attributes using Generative Adversarial Networks (GANs). Given the face images corresponding to two unique data subjects, the proposed CFIA method will independently generate the segmented facial attributes, then blend them using transparent masks to generate the CFIA samples. We generate 526 unique CFIA combinations of facial attributes for each pair of contributory data subjects. Extensive experiments are carried out on our newly generated CFIA dataset consisting of 1000 unique identities with 2000 bona fide samples and 526000 CFIA samples, thus resulting in an overall 528000 face image samples. We present a sequence of experiments to benchmark the attack potential of CFIA samples using four different automatic FRS. We introduced a new metric named Generalized Morphing Attack Potential (G-MAP) to benchmark the vulnerability of generated attacks on FRS effectively. Additional experiments are performed on the representative subset of the CFIA dataset to benchmark both perceptual quality and human observer response. Finally, the CFIA detection performance is benchmarked using three different single image based face Morphing Attack Detection (MAD) algorithms. The source code of the proposed method together with CFIA dataset will be made publicly available: <uri>https://github.com/jagmohaniiit/LatentCompositionCode</uri>https://ieeexplore.ieee.org/document/10078862/Biometricsface recognitionmorphing attacksimage compositingvulnerabilitygeneralized morphing attack potential |
| spellingShingle | Jag Mohan Singh Raghavendra Ramachandra Deep Composite Face Image Attacks: Generation, Vulnerability and Detection IEEE Access Biometrics face recognition morphing attacks image compositing vulnerability generalized morphing attack potential |
| title | Deep Composite Face Image Attacks: Generation, Vulnerability and Detection |
| title_full | Deep Composite Face Image Attacks: Generation, Vulnerability and Detection |
| title_fullStr | Deep Composite Face Image Attacks: Generation, Vulnerability and Detection |
| title_full_unstemmed | Deep Composite Face Image Attacks: Generation, Vulnerability and Detection |
| title_short | Deep Composite Face Image Attacks: Generation, Vulnerability and Detection |
| title_sort | deep composite face image attacks generation vulnerability and detection |
| topic | Biometrics face recognition morphing attacks image compositing vulnerability generalized morphing attack potential |
| url | https://ieeexplore.ieee.org/document/10078862/ |
| work_keys_str_mv | AT jagmohansingh deepcompositefaceimageattacksgenerationvulnerabilityanddetection AT raghavendraramachandra deepcompositefaceimageattacksgenerationvulnerabilityanddetection |