Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking
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_ | 1866910377979150336 |
|---|---|
| author | Guo, Qianyu Fu, Jiaming Lu, Yawen Gan, Dongming |
| author_facet | Guo, Qianyu Fu, Jiaming Lu, Yawen Gan, Dongming |
| contents | In Virtual Reality (VR), adversarial attack remains a significant security threat. Most deep learning-based methods for physical and digital adversarial attacks focus on enhancing attack performance by crafting adversarial examples that contain large printable distortions that are easy for human observers to identify. However, attackers rarely impose limitations on the naturalness and comfort of the appearance of the generated attack image, resulting in a noticeable and unnatural attack. To address this challenge, we propose a framework to incorporate style transfer to craft adversarial inputs of natural styles that exhibit minimal detectability and maximum natural appearance, while maintaining superior attack capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14778 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking Guo, Qianyu Fu, Jiaming Lu, Yawen Gan, Dongming Computer Vision and Pattern Recognition Image and Video Processing In Virtual Reality (VR), adversarial attack remains a significant security threat. Most deep learning-based methods for physical and digital adversarial attacks focus on enhancing attack performance by crafting adversarial examples that contain large printable distortions that are easy for human observers to identify. However, attackers rarely impose limitations on the naturalness and comfort of the appearance of the generated attack image, resulting in a noticeable and unnatural attack. To address this challenge, we propose a framework to incorporate style transfer to craft adversarial inputs of natural styles that exhibit minimal detectability and maximum natural appearance, while maintaining superior attack capabilities. |
| title | Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2403.14778 |