Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912114812125184 |
|---|---|
| author | Blasingame, Zander W. Liu, Chen |
| author_facet | Blasingame, Zander W. Liu, Chen |
| contents | Morphing attacks are an emerging threat to state-of-the-art Face Recognition (FR) systems, which aim to create a single image that contains the biometric information of multiple identities. Diffusion Morphs (DiM) are a recently proposed morphing attack that has achieved state-of-the-art performance for representation-based morphing attacks. However, none of the existing research on DiMs have leveraged the iterative nature of DiMs and left the DiM model as a black box, treating it no differently than one would a Generative Adversarial Network (GAN) or Varational AutoEncoder (VAE). We propose a greedy strategy on the iterative sampling process of DiM models which searches for an optimal step guided by an identity-based heuristic function. We compare our proposed algorithm against ten other state-of-the-art morphing algorithms using the open-source SYN-MAD 2022 competition dataset. We find that our proposed algorithm is unreasonably effective, fooling all of the tested FR systems with an MMPMR of 100%, outperforming all other morphing algorithms compared. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06025 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs Blasingame, Zander W. Liu, Chen Computer Vision and Pattern Recognition Artificial Intelligence Morphing attacks are an emerging threat to state-of-the-art Face Recognition (FR) systems, which aim to create a single image that contains the biometric information of multiple identities. Diffusion Morphs (DiM) are a recently proposed morphing attack that has achieved state-of-the-art performance for representation-based morphing attacks. However, none of the existing research on DiMs have leveraged the iterative nature of DiMs and left the DiM model as a black box, treating it no differently than one would a Generative Adversarial Network (GAN) or Varational AutoEncoder (VAE). We propose a greedy strategy on the iterative sampling process of DiM models which searches for an optimal step guided by an identity-based heuristic function. We compare our proposed algorithm against ten other state-of-the-art morphing algorithms using the open-source SYN-MAD 2022 competition dataset. We find that our proposed algorithm is unreasonably effective, fooling all of the tested FR systems with an MMPMR of 100%, outperforming all other morphing algorithms compared. |
| title | Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.06025 |