Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909180353314816 |
|---|---|
| author | Chen, Erh-Chung Chen, Pin-Yu Chung, I-Hsin Lee, Che-Rung |
| author_facet | Chen, Erh-Chung Chen, Pin-Yu Chung, I-Hsin Lee, Che-Rung |
| contents | Latency attacks against object detection represent a variant of adversarial attacks that aim to inflate the inference time by generating additional ghost objects in a target image. However, generating ghost objects in the black-box scenario remains a challenge since information about these unqualified objects remains opaque. In this study, we demonstrate the feasibility of generating ghost objects in adversarial examples by extending the concept of "steal now, decrypt later" attacks. These adversarial examples, once produced, can be employed to exploit potential vulnerabilities in the AI service, giving rise to significant security concerns. The experimental results demonstrate that the proposed attack achieves successful attacks across various commonly used models and Google Vision API without any prior knowledge about the target model. Additionally, the average cost of each attack is less than \$ 1 dollars, posing a significant threat to AI security. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15881 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks Chen, Erh-Chung Chen, Pin-Yu Chung, I-Hsin Lee, Che-Rung Computer Vision and Pattern Recognition Artificial Intelligence Latency attacks against object detection represent a variant of adversarial attacks that aim to inflate the inference time by generating additional ghost objects in a target image. However, generating ghost objects in the black-box scenario remains a challenge since information about these unqualified objects remains opaque. In this study, we demonstrate the feasibility of generating ghost objects in adversarial examples by extending the concept of "steal now, decrypt later" attacks. These adversarial examples, once produced, can be employed to exploit potential vulnerabilities in the AI service, giving rise to significant security concerns. The experimental results demonstrate that the proposed attack achieves successful attacks across various commonly used models and Google Vision API without any prior knowledge about the target model. Additionally, the average cost of each attack is less than \$ 1 dollars, posing a significant threat to AI security. |
| title | Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.15881 |