Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.00266 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914358891642880 |
|---|---|
| author | Li, He He, Wenyue Kong, Weihang Zhang, Xingchen |
| author_facet | Li, He He, Wenyue Kong, Weihang Zhang, Xingchen |
| contents | Multimodal adversarial attacks for dense prediction remain largely underexplored. In particular, visual-infrared (VI) perception systems introduce unique challenges due to heterogeneous spectral characteristics and modality-specific intensity distributions. Existing adversarial patch methods are primarily designed for single-modal inputs and fail to account for crossspectral inconsistencies, leading to reduced attack effectiveness and poor stealthiness when applied to VI dense prediction models. To address these challenges, we propose a joint position-color optimization framework (AP-PCO) for generating adversarial patches in visual-infrared settings. The proposed method optimizes patch placement and color composition simultaneously using a fitness function derived from model outputs, enabling a single patch to perturb both visible and infrared modalities. To further bridge spectral discrepancies, we introduce a crossmodal color adaptation strategy that constrains patch appearance according to infrared grayscale characteristics while maintaining strong perturbations in the visible domain, thereby reducing cross-spectral saliency. The optimization procedure operates without requiring internal model information, supporting flexible black-box attacks. Extensive experiments on visual-infrared dense prediction tasks demonstrate that the proposed AP-PCO achieves consistently strong attack performance across multiple architectures, providing a practical benchmark for robustness evaluation in VI perception systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00266 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adversarial Patch Generation for Visual-Infrared Dense Prediction Tasks via Joint Position-Color Optimization Li, He He, Wenyue Kong, Weihang Zhang, Xingchen Computer Vision and Pattern Recognition Multimodal adversarial attacks for dense prediction remain largely underexplored. In particular, visual-infrared (VI) perception systems introduce unique challenges due to heterogeneous spectral characteristics and modality-specific intensity distributions. Existing adversarial patch methods are primarily designed for single-modal inputs and fail to account for crossspectral inconsistencies, leading to reduced attack effectiveness and poor stealthiness when applied to VI dense prediction models. To address these challenges, we propose a joint position-color optimization framework (AP-PCO) for generating adversarial patches in visual-infrared settings. The proposed method optimizes patch placement and color composition simultaneously using a fitness function derived from model outputs, enabling a single patch to perturb both visible and infrared modalities. To further bridge spectral discrepancies, we introduce a crossmodal color adaptation strategy that constrains patch appearance according to infrared grayscale characteristics while maintaining strong perturbations in the visible domain, thereby reducing cross-spectral saliency. The optimization procedure operates without requiring internal model information, supporting flexible black-box attacks. Extensive experiments on visual-infrared dense prediction tasks demonstrate that the proposed AP-PCO achieves consistently strong attack performance across multiple architectures, providing a practical benchmark for robustness evaluation in VI perception systems. |
| title | Adversarial Patch Generation for Visual-Infrared Dense Prediction Tasks via Joint Position-Color Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.00266 |