Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection
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_ | 1866913442210775040 |
|---|---|
| author | Zhang, Youqian Yang, Chunxi Fu, Eugene Y. Jiang, Qinhong Yan, Chen Chau, Sze-Yiu Ngai, Grace Leong, Hong-Va Luo, Xiapu Xu, Wenyuan |
| author_facet | Zhang, Youqian Yang, Chunxi Fu, Eugene Y. Jiang, Qinhong Yan, Chen Chau, Sze-Yiu Ngai, Grace Leong, Hong-Va Luo, Xiapu Xu, Wenyuan |
| contents | Object detection can localize and identify objects in images, and it is extensively employed in critical multimedia applications such as security surveillance and autonomous driving. Despite the success of existing object detection models, they are often evaluated in ideal scenarios where captured images guarantee the accurate and complete representation of the detecting scenes. However, images captured by image sensors may be affected by different factors in real applications, including cyber-physical attacks. In particular, attackers can exploit hardware properties within the systems to inject electromagnetic interference so as to manipulate the images. Such attacks can cause noisy or incomplete information about the captured scene, leading to incorrect detection results, potentially granting attackers malicious control over critical functions of the systems. This paper presents a research work that comprehensively quantifies and analyzes the impacts of such attacks on state-of-the-art object detection models in practice. It also sheds light on the underlying reasons for the incorrect detection outcomes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16327 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection Zhang, Youqian Yang, Chunxi Fu, Eugene Y. Jiang, Qinhong Yan, Chen Chau, Sze-Yiu Ngai, Grace Leong, Hong-Va Luo, Xiapu Xu, Wenyuan Cryptography and Security Computer Vision and Pattern Recognition Object detection can localize and identify objects in images, and it is extensively employed in critical multimedia applications such as security surveillance and autonomous driving. Despite the success of existing object detection models, they are often evaluated in ideal scenarios where captured images guarantee the accurate and complete representation of the detecting scenes. However, images captured by image sensors may be affected by different factors in real applications, including cyber-physical attacks. In particular, attackers can exploit hardware properties within the systems to inject electromagnetic interference so as to manipulate the images. Such attacks can cause noisy or incomplete information about the captured scene, leading to incorrect detection results, potentially granting attackers malicious control over critical functions of the systems. This paper presents a research work that comprehensively quantifies and analyzes the impacts of such attacks on state-of-the-art object detection models in practice. It also sheds light on the underlying reasons for the incorrect detection outcomes. |
| title | Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.16327 |