Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation
Deepfake images, synthetic images created using digital software, continue to present a serious threat to online platforms. This is especially relevant for biometric verification systems, as deepfakes that attempt to bypass such measures increase the risk of impersonation, identity theft and scams....
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/14/6/225 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839654401059323904 |
|---|---|
| author | Hilary Zen Rohan Wagh Miguel Wanderley Gustavo Bicalho Rachel Park Megan Sun Rafael Palacios Lucas Carvalho Guilherme Rinaldo Amar Gupta |
| author_facet | Hilary Zen Rohan Wagh Miguel Wanderley Gustavo Bicalho Rachel Park Megan Sun Rafael Palacios Lucas Carvalho Guilherme Rinaldo Amar Gupta |
| author_sort | Hilary Zen |
| collection | DOAJ |
| description | Deepfake images, synthetic images created using digital software, continue to present a serious threat to online platforms. This is especially relevant for biometric verification systems, as deepfakes that attempt to bypass such measures increase the risk of impersonation, identity theft and scams. Although research on deepfake image detection has provided many high-performing classifiers, many of these commonly used detection models lack generalizability across different methods of deepfake generation. For companies and governments fighting identify fraud, a lack of generalization is challenging, as malicious actors may use a variety of deepfake image-generation methods available through online wrappers. This work explores if combining multiple classifiers into an ensemble model can improve generalization without losing performance across different generation methods. It also considers current methods of deepfake image generation, with a focus on publicly available and easily accessible methods. We compare our framework against its underlying models to show how companies can better respond to emerging deepfake generation methods. |
| format | Article |
| id | doaj-art-d99e865f43c14d4fade46c0a9f4c9419 |
| institution | Matheson Library |
| issn | 2073-431X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj-art-d99e865f43c14d4fade46c0a9f4c94192025-06-25T13:39:47ZengMDPI AGComputers2073-431X2025-06-0114622510.3390/computers14060225Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image GenerationHilary Zen0Rohan Wagh1Miguel Wanderley2Gustavo Bicalho3Rachel Park4Megan Sun5Rafael Palacios6Lucas Carvalho7Guilherme Rinaldo8Amar Gupta9Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA 02139, USADepartment of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA 02139, USAInstituto de Ciência e Tecnologia Itaú -ICTi, Av. Engenheiro Armando de Arruda Pereira 774, Jabaquara - São Paulo, São Paulo 04308-000, BrazilInstituto de Ciência e Tecnologia Itaú -ICTi, Av. Engenheiro Armando de Arruda Pereira 774, Jabaquara - São Paulo, São Paulo 04308-000, BrazilDepartment of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA 02139, USADepartment of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA 02139, USACybersecurity at MIT Sloan (CAMS), Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA 02139, USAInstituto de Ciência e Tecnologia Itaú -ICTi, Av. Engenheiro Armando de Arruda Pereira 774, Jabaquara - São Paulo, São Paulo 04308-000, BrazilInstituto de Ciência e Tecnologia Itaú -ICTi, Av. Engenheiro Armando de Arruda Pereira 774, Jabaquara - São Paulo, São Paulo 04308-000, BrazilDepartment of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA 02139, USADeepfake images, synthetic images created using digital software, continue to present a serious threat to online platforms. This is especially relevant for biometric verification systems, as deepfakes that attempt to bypass such measures increase the risk of impersonation, identity theft and scams. Although research on deepfake image detection has provided many high-performing classifiers, many of these commonly used detection models lack generalizability across different methods of deepfake generation. For companies and governments fighting identify fraud, a lack of generalization is challenging, as malicious actors may use a variety of deepfake image-generation methods available through online wrappers. This work explores if combining multiple classifiers into an ensemble model can improve generalization without losing performance across different generation methods. It also considers current methods of deepfake image generation, with a focus on publicly available and easily accessible methods. We compare our framework against its underlying models to show how companies can better respond to emerging deepfake generation methods.https://www.mdpi.com/2073-431X/14/6/225deepfakesbiometric verification systemsgeneralizationensemble learningdeepfake detection model |
| spellingShingle | Hilary Zen Rohan Wagh Miguel Wanderley Gustavo Bicalho Rachel Park Megan Sun Rafael Palacios Lucas Carvalho Guilherme Rinaldo Amar Gupta Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation Computers deepfakes biometric verification systems generalization ensemble learning deepfake detection model |
| title | Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation |
| title_full | Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation |
| title_fullStr | Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation |
| title_full_unstemmed | Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation |
| title_short | Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation |
| title_sort | ensemble based biometric verification defending against multi strategy deepfake image generation |
| topic | deepfakes biometric verification systems generalization ensemble learning deepfake detection model |
| url | https://www.mdpi.com/2073-431X/14/6/225 |
| work_keys_str_mv | AT hilaryzen ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT rohanwagh ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT miguelwanderley ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT gustavobicalho ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT rachelpark ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT megansun ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT rafaelpalacios ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT lucascarvalho ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT guilhermerinaldo ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration AT amargupta ensemblebasedbiometricverificationdefendingagainstmultistrategydeepfakeimagegeneration |