Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models
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_ | 1866914443495997440 |
|---|---|
| author | Hu, Chengyin Dong, Yuxian Guo, Yikun Chen, Xiang Wu, Junqi Long, Jiahuan Wei, Yiwei Jiang, Tingsong Yao, Wen |
| author_facet | Hu, Chengyin Dong, Yuxian Guo, Yikun Chen, Xiang Wu, Junqi Long, Jiahuan Wei, Yiwei Jiang, Tingsong Yao, Wen |
| contents | Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception in low-visibility environments, yet their robustness to adversarial attacks remains largely unexplored. Existing adversarial patch methods are mainly designed for RGB-based models in closed-set settings and are not readily applicable to the open-ended semantic understanding and physical deployment requirements of infrared VLMs. To bridge this gap, we propose Universal Curved-Grid Patch (UCGP), a universal physical adversarial patch framework for IR-VLMs. UCGP integrates Curved-Grid Mesh (CGM) parameterization for continuous, low-frequency, and deployable patch generation with a unified representation-driven objective that promotes subspace departure, topology disruption, and stealth. To improve robustness under real-world deployment and domain shift, we further incorporate Meta Differential Evolution and EOT-augmented TPS deformation modeling. Rather than manipulating labels or prompts, UCGP directly disrupts the visual representation space, weakening cross-modal semantic alignment. Extensive experiments demonstrate that UCGP consistently compromises semantic understanding across diverse IR-VLM architectures while maintaining cross-model transferability, cross-dataset generalization, real-world physical effectiveness, and robustness against defenses. These findings reveal a previously overlooked robustness vulnerability in current infrared multimodal systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03117 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models Hu, Chengyin Dong, Yuxian Guo, Yikun Chen, Xiang Wu, Junqi Long, Jiahuan Wei, Yiwei Jiang, Tingsong Yao, Wen Computer Vision and Pattern Recognition Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception in low-visibility environments, yet their robustness to adversarial attacks remains largely unexplored. Existing adversarial patch methods are mainly designed for RGB-based models in closed-set settings and are not readily applicable to the open-ended semantic understanding and physical deployment requirements of infrared VLMs. To bridge this gap, we propose Universal Curved-Grid Patch (UCGP), a universal physical adversarial patch framework for IR-VLMs. UCGP integrates Curved-Grid Mesh (CGM) parameterization for continuous, low-frequency, and deployable patch generation with a unified representation-driven objective that promotes subspace departure, topology disruption, and stealth. To improve robustness under real-world deployment and domain shift, we further incorporate Meta Differential Evolution and EOT-augmented TPS deformation modeling. Rather than manipulating labels or prompts, UCGP directly disrupts the visual representation space, weakening cross-modal semantic alignment. Extensive experiments demonstrate that UCGP consistently compromises semantic understanding across diverse IR-VLM architectures while maintaining cross-model transferability, cross-dataset generalization, real-world physical effectiveness, and robustness against defenses. These findings reveal a previously overlooked robustness vulnerability in current infrared multimodal systems. |
| title | Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.03117 |