Detecting Face Synthesis Using a Concealed Fusion Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929203955367936 |
|---|---|
| author | Leyva, Roberto Sanchez, Victor Epiphaniou, Gregory Maple, Carsten |
| author_facet | Leyva, Roberto Sanchez, Victor Epiphaniou, Gregory Maple, Carsten |
| contents | Face image synthesis is gaining more attention in computer security due to concerns about its potential negative impacts, including those related to fake biometrics. Hence, building models that can detect the synthesized face images is an important challenge to tackle. In this paper, we propose a fusion-based strategy to detect face image synthesis while providing resiliency to several attacks. The proposed strategy uses a late fusion of the outputs computed by several undisclosed models by relying on random polynomial coefficients and exponents to conceal a new feature space. Unlike existing concealing solutions, our strategy requires no quantization, which helps to preserve the feature space. Our experiments reveal that our strategy achieves state-of-the-art performance while providing protection against poisoning, perturbation, backdoor, and reverse model attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04257 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Detecting Face Synthesis Using a Concealed Fusion Model Leyva, Roberto Sanchez, Victor Epiphaniou, Gregory Maple, Carsten Computer Vision and Pattern Recognition Face image synthesis is gaining more attention in computer security due to concerns about its potential negative impacts, including those related to fake biometrics. Hence, building models that can detect the synthesized face images is an important challenge to tackle. In this paper, we propose a fusion-based strategy to detect face image synthesis while providing resiliency to several attacks. The proposed strategy uses a late fusion of the outputs computed by several undisclosed models by relying on random polynomial coefficients and exponents to conceal a new feature space. Unlike existing concealing solutions, our strategy requires no quantization, which helps to preserve the feature space. Our experiments reveal that our strategy achieves state-of-the-art performance while providing protection against poisoning, perturbation, backdoor, and reverse model attacks. |
| title | Detecting Face Synthesis Using a Concealed Fusion Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.04257 |