Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913627305410560 |
|---|---|
| author | Tang, Keke Ke, Weiyao Peng, Weilong Wang, Xiaofei Du, Ziyong Wu, Zhize Zhu, Peican Tian, Zhihong |
| author_facet | Tang, Keke Ke, Weiyao Peng, Weilong Wang, Xiaofei Du, Ziyong Wu, Zhize Zhu, Peican Tian, Zhihong |
| contents | Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Traditional solutions strictly limit point displacement during attacks, making it challenging to balance imperceptibility with adversarial effectiveness. In this paper, we attribute the inadequate imperceptibility of adversarial attacks on point clouds to deviations from the underlying surface. To address this, we introduce a novel point-to-surface (P2S) field that adjusts adversarial perturbation directions by dragging points back to their original underlying surface. Specifically, we use a denoising network to learn the gradient field of the logarithmic density function encoding the shape's surface, and apply a distance-aware adjustment to perturbation directions during attacks, thereby enhancing imperceptibility. Extensive experiments show that adversarial attacks guided by our P2S field are more imperceptible, outperforming state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19015 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field Tang, Keke Ke, Weiyao Peng, Weilong Wang, Xiaofei Du, Ziyong Wu, Zhize Zhu, Peican Tian, Zhihong Computer Vision and Pattern Recognition Cryptography and Security 68T07 Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Traditional solutions strictly limit point displacement during attacks, making it challenging to balance imperceptibility with adversarial effectiveness. In this paper, we attribute the inadequate imperceptibility of adversarial attacks on point clouds to deviations from the underlying surface. To address this, we introduce a novel point-to-surface (P2S) field that adjusts adversarial perturbation directions by dragging points back to their original underlying surface. Specifically, we use a denoising network to learn the gradient field of the logarithmic density function encoding the shape's surface, and apply a distance-aware adjustment to perturbation directions during attacks, thereby enhancing imperceptibility. Extensive experiments show that adversarial attacks guided by our P2S field are more imperceptible, outperforming state-of-the-art methods. |
| title | Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field |
| topic | Computer Vision and Pattern Recognition Cryptography and Security 68T07 |
| url | https://arxiv.org/abs/2412.19015 |