Adversarial Camouflage
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910065584242688 |
|---|---|
| author | Borsukiewicz, Paweł Lunghi, Daniele Tessa, Melissa Klein, Jacques Bissyandé, Tegawendé F. |
| author_facet | Borsukiewicz, Paweł Lunghi, Daniele Tessa, Melissa Klein, Jacques Bissyandé, Tegawendé F. |
| contents | While the rapid development of facial recognition algorithms has enabled numerous beneficial applications, their widespread deployment has raised significant concerns about the risks of mass surveillance and threats to individual privacy. In this paper, we introduce \textit{Adversarial Camouflage} as a novel solution for protecting users' privacy. This approach is designed to be efficient and simple to reproduce for users in the physical world. The algorithm starts by defining a low-dimensional pattern space parameterized by color, shape, and angle. Optimized patterns, once found, are projected onto semantically valid facial regions for evaluation. Our method maximizes recognition error across multiple architectures, ensuring high cross-model transferability even against black-box systems. It significantly degrades the performance of all tested state-of-the-art face recognition models during simulations and demonstrates promising results in real-world human experiments, while revealing differences in model robustness and evidence of attack transferability across architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21867 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adversarial Camouflage Borsukiewicz, Paweł Lunghi, Daniele Tessa, Melissa Klein, Jacques Bissyandé, Tegawendé F. Computer Vision and Pattern Recognition Artificial Intelligence While the rapid development of facial recognition algorithms has enabled numerous beneficial applications, their widespread deployment has raised significant concerns about the risks of mass surveillance and threats to individual privacy. In this paper, we introduce \textit{Adversarial Camouflage} as a novel solution for protecting users' privacy. This approach is designed to be efficient and simple to reproduce for users in the physical world. The algorithm starts by defining a low-dimensional pattern space parameterized by color, shape, and angle. Optimized patterns, once found, are projected onto semantically valid facial regions for evaluation. Our method maximizes recognition error across multiple architectures, ensuring high cross-model transferability even against black-box systems. It significantly degrades the performance of all tested state-of-the-art face recognition models during simulations and demonstrates promising results in real-world human experiments, while revealing differences in model robustness and evidence of attack transferability across architectures. |
| title | Adversarial Camouflage |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.21867 |