Adversarial liveness detector: Leveraging adversarial perturbations in fingerprint liveness detection
Abstract The widespread use of fingerprint authentication systems (FASs) in consumer electronics opens for the development of advanced presentation attacks, that is, procedures designed to bypass a FAS using a forged fingerprint. As a consequence, FAS are often equipped with a fingerprint presentati...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-IET
2023-03-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12106 |
| _version_ | 1797426925280428032 |
|---|---|
| author | Antonio Galli Michela Gravina Stefano Marrone Domenico Mattiello Carlo Sansone |
| author_facet | Antonio Galli Michela Gravina Stefano Marrone Domenico Mattiello Carlo Sansone |
| author_sort | Antonio Galli |
| collection | DOAJ |
| description | Abstract The widespread use of fingerprint authentication systems (FASs) in consumer electronics opens for the development of advanced presentation attacks, that is, procedures designed to bypass a FAS using a forged fingerprint. As a consequence, FAS are often equipped with a fingerprint presentation attack detection (FPAD) module, to recognise live fingerprints from fake replicas. In this work, a novel FPAD approach based on Convolutional Neural Networks (CNNs) and on an ad hoc adversarial data augmentation strategy designed to iteratively increase the considered detector robustness is proposed. In particular, the concept of adversarial fingerprint, that is, fake fingerprints disguised by using ad hoc fingerprint adversarial perturbation algorithms was leveraged to help the detector focus only on salient portions of the fingerprints. The procedure can be adapted to different CNNs, adversarial fingerprint algorithms and fingerprint scanners, making the proposed approach versatile and easily customisable todifferent working scenarios. To test the effectiveness of the proposed approach, the authors took part in the LivDet 2021 competition, an international challenge gathering experts to compete on fingerprint liveness detection under different scanners and fake replica generation approach, achieving first place out of 23 participants in the ‘Liveness Detection in Action track’. |
| first_indexed | 2024-03-09T08:36:55Z |
| format | Article |
| id | doaj.art-6de4548f144c48a4a6edf14c08126728 |
| institution | Directory Open Access Journal |
| issn | 2047-4938 2047-4946 |
| language | English |
| last_indexed | 2024-03-09T08:36:55Z |
| publishDate | 2023-03-01 |
| publisher | Hindawi-IET |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj.art-6de4548f144c48a4a6edf14c081267282023-12-02T17:53:14ZengHindawi-IETIET Biometrics2047-49382047-49462023-03-0112210211110.1049/bme2.12106Adversarial liveness detector: Leveraging adversarial perturbations in fingerprint liveness detectionAntonio Galli0Michela Gravina1Stefano Marrone2Domenico Mattiello3Carlo Sansone4Department of Electrical and Information Technology (DIETI) University of Naples Federico II Naples ItalyDepartment of Electrical and Information Technology (DIETI) University of Naples Federico II Naples ItalyDepartment of Electrical and Information Technology (DIETI) University of Naples Federico II Naples ItalyDepartment of Electrical and Information Technology (DIETI) University of Naples Federico II Naples ItalyDepartment of Electrical and Information Technology (DIETI) University of Naples Federico II Naples ItalyAbstract The widespread use of fingerprint authentication systems (FASs) in consumer electronics opens for the development of advanced presentation attacks, that is, procedures designed to bypass a FAS using a forged fingerprint. As a consequence, FAS are often equipped with a fingerprint presentation attack detection (FPAD) module, to recognise live fingerprints from fake replicas. In this work, a novel FPAD approach based on Convolutional Neural Networks (CNNs) and on an ad hoc adversarial data augmentation strategy designed to iteratively increase the considered detector robustness is proposed. In particular, the concept of adversarial fingerprint, that is, fake fingerprints disguised by using ad hoc fingerprint adversarial perturbation algorithms was leveraged to help the detector focus only on salient portions of the fingerprints. The procedure can be adapted to different CNNs, adversarial fingerprint algorithms and fingerprint scanners, making the proposed approach versatile and easily customisable todifferent working scenarios. To test the effectiveness of the proposed approach, the authors took part in the LivDet 2021 competition, an international challenge gathering experts to compete on fingerprint liveness detection under different scanners and fake replica generation approach, achieving first place out of 23 participants in the ‘Liveness Detection in Action track’.https://doi.org/10.1049/bme2.12106biometrics presentation attack detectionlearning (artificial intelligence)liveness detection |
| spellingShingle | Antonio Galli Michela Gravina Stefano Marrone Domenico Mattiello Carlo Sansone Adversarial liveness detector: Leveraging adversarial perturbations in fingerprint liveness detection IET Biometrics biometrics presentation attack detection learning (artificial intelligence) liveness detection |
| title | Adversarial liveness detector: Leveraging adversarial perturbations in fingerprint liveness detection |
| title_full | Adversarial liveness detector: Leveraging adversarial perturbations in fingerprint liveness detection |
| title_fullStr | Adversarial liveness detector: Leveraging adversarial perturbations in fingerprint liveness detection |
| title_full_unstemmed | Adversarial liveness detector: Leveraging adversarial perturbations in fingerprint liveness detection |
| title_short | Adversarial liveness detector: Leveraging adversarial perturbations in fingerprint liveness detection |
| title_sort | adversarial liveness detector leveraging adversarial perturbations in fingerprint liveness detection |
| topic | biometrics presentation attack detection learning (artificial intelligence) liveness detection |
| url | https://doi.org/10.1049/bme2.12106 |
| work_keys_str_mv | AT antoniogalli adversariallivenessdetectorleveragingadversarialperturbationsinfingerprintlivenessdetection AT michelagravina adversariallivenessdetectorleveragingadversarialperturbationsinfingerprintlivenessdetection AT stefanomarrone adversariallivenessdetectorleveragingadversarialperturbationsinfingerprintlivenessdetection AT domenicomattiello adversariallivenessdetectorleveragingadversarialperturbationsinfingerprintlivenessdetection AT carlosansone adversariallivenessdetectorleveragingadversarialperturbationsinfingerprintlivenessdetection |