Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914860493701120 |
|---|---|
| author | Tiliwalidi, Kalibinuer Hu, Chengyin Shi, Weiwen |
| author_facet | Tiliwalidi, Kalibinuer Hu, Chengyin Shi, Weiwen |
| contents | While extensive research exists on physical adversarial attacks within the visible spectrum, studies on such techniques in the infrared spectrum are limited. Infrared object detectors are vital in modern technological applications but are susceptible to adversarial attacks, posing significant security threats. Previous studies using physical perturbations like light bulb arrays and aerogels for white-box attacks, or hot and cold patches for black-box attacks, have proven impractical or limited in multi-view support. To address these issues, we propose the Adversarial Infrared Grid (AdvGrid), which models perturbations in a grid format and uses a genetic algorithm for black-box optimization. These perturbations are cyclically applied to various parts of a pedestrian's clothing to facilitate multi-view black-box physical attacks on infrared pedestrian detectors. Extensive experiments validate AdvGrid's effectiveness, stealthiness, and robustness. The method achieves attack success rates of 80.00\% in digital environments and 91.86\% in physical environments, outperforming baseline methods. Additionally, the average attack success rate exceeds 50\% against mainstream detectors, demonstrating AdvGrid's robustness. Our analyses include ablation studies, transfer attacks, and adversarial defenses, confirming the method's superiority. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01168 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid Tiliwalidi, Kalibinuer Hu, Chengyin Shi, Weiwen Computer Vision and Pattern Recognition Artificial Intelligence While extensive research exists on physical adversarial attacks within the visible spectrum, studies on such techniques in the infrared spectrum are limited. Infrared object detectors are vital in modern technological applications but are susceptible to adversarial attacks, posing significant security threats. Previous studies using physical perturbations like light bulb arrays and aerogels for white-box attacks, or hot and cold patches for black-box attacks, have proven impractical or limited in multi-view support. To address these issues, we propose the Adversarial Infrared Grid (AdvGrid), which models perturbations in a grid format and uses a genetic algorithm for black-box optimization. These perturbations are cyclically applied to various parts of a pedestrian's clothing to facilitate multi-view black-box physical attacks on infrared pedestrian detectors. Extensive experiments validate AdvGrid's effectiveness, stealthiness, and robustness. The method achieves attack success rates of 80.00\% in digital environments and 91.86\% in physical environments, outperforming baseline methods. Additionally, the average attack success rate exceeds 50\% against mainstream detectors, demonstrating AdvGrid's robustness. Our analyses include ablation studies, transfer attacks, and adversarial defenses, confirming the method's superiority. |
| title | Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.01168 |