Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914428950151168 |
|---|---|
| author | Hu, Chengyin Guo, Yikun Dong, Yuxian Zhang, Qike Tiliwalidi, Kalibinuer Wei, Yiwei Shi, Haitao Guo, Jiujiang Long, Jiahuan Chen, Xiang |
| author_facet | Hu, Chengyin Guo, Yikun Dong, Yuxian Zhang, Qike Tiliwalidi, Kalibinuer Wei, Yiwei Shi, Haitao Guo, Jiujiang Long, Jiahuan Chen, Xiang |
| contents | Although infrared pedestrian detectors have been widely deployed in visual perception tasks, their vulnerability to physical adversarial attacks is becoming increasingly apparent. Existing physical attack methods predominantly rely on instance-specific online optimization and rigid pattern design, leading to high deployment costs and insufficient physical robustness. To address these limitations, this work proposes the Universal Physical Patch Attack (UPPA), the first universal physical attack method in the infrared domain. This method employs geometrically constrained parameterized Bezier blocks to model perturbations and utilizes the Particle Swarm Optimization (PSO) algorithm to perform unified optimization across the global data distribution, thus maintaining topological stability under dynamic deformations. In the physical deployment phase, we materialize the optimized digital perturbations into physical cold patches, achieving a continuous and smooth low-temperature distribution that naturally aligns with the thermal radiation characteristics of infrared imaging. Extensive experiments demonstrate that UPPA achieves an outstanding physical attack success rate without any online computational overhead, while also exhibiting strong cross-domain generalization and reliable black-box transferability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21876 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems Hu, Chengyin Guo, Yikun Dong, Yuxian Zhang, Qike Tiliwalidi, Kalibinuer Wei, Yiwei Shi, Haitao Guo, Jiujiang Long, Jiahuan Chen, Xiang Computer Vision and Pattern Recognition Although infrared pedestrian detectors have been widely deployed in visual perception tasks, their vulnerability to physical adversarial attacks is becoming increasingly apparent. Existing physical attack methods predominantly rely on instance-specific online optimization and rigid pattern design, leading to high deployment costs and insufficient physical robustness. To address these limitations, this work proposes the Universal Physical Patch Attack (UPPA), the first universal physical attack method in the infrared domain. This method employs geometrically constrained parameterized Bezier blocks to model perturbations and utilizes the Particle Swarm Optimization (PSO) algorithm to perform unified optimization across the global data distribution, thus maintaining topological stability under dynamic deformations. In the physical deployment phase, we materialize the optimized digital perturbations into physical cold patches, achieving a continuous and smooth low-temperature distribution that naturally aligns with the thermal radiation characteristics of infrared imaging. Extensive experiments demonstrate that UPPA achieves an outstanding physical attack success rate without any online computational overhead, while also exhibiting strong cross-domain generalization and reliable black-box transferability. |
| title | Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.21876 |