Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2501.11901 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917970896224256 |
|---|---|
| author | Liu, Hangyu Peng, Bo Cui, Can Ding, Pengxiang Wang, Donglin |
| author_facet | Liu, Hangyu Peng, Bo Cui, Can Ding, Pengxiang Wang, Donglin |
| contents | Deep Neural Networks (DNNs) are highly vulnerable to adversarial examples, which pose significant challenges in security-sensitive applications. Among various adversarial attack strategies, input transformation-based attacks have demonstrated remarkable effectiveness in enhancing adversarial transferability. However, existing methods still perform poorly across different architectures, even though they have achieved promising results within the same architecture. This limitation arises because, while models of the same architecture may focus on different regions of the object, the variation is even more pronounced across different architectures. Unfortunately, current approaches fail to effectively guide models to attend to these diverse regions. To address this issue, this paper proposes a novel input transformation-based attack method, termed Component-Wise Transformation (CWT). CWT applies interpolation and selective rotation to individual image blocks, ensuring that each transformed image highlights different target regions, thereby improving the transferability of adversarial examples. Extensive experiments on the standard ImageNet dataset show that CWT consistently outperforms state-of-the-art methods in both attack success rates and stability across CNN- and Transformer-based models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_11901 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Adversarial Transferability via Component-Wise Transformation Liu, Hangyu Peng, Bo Cui, Can Ding, Pengxiang Wang, Donglin Computer Vision and Pattern Recognition Deep Neural Networks (DNNs) are highly vulnerable to adversarial examples, which pose significant challenges in security-sensitive applications. Among various adversarial attack strategies, input transformation-based attacks have demonstrated remarkable effectiveness in enhancing adversarial transferability. However, existing methods still perform poorly across different architectures, even though they have achieved promising results within the same architecture. This limitation arises because, while models of the same architecture may focus on different regions of the object, the variation is even more pronounced across different architectures. Unfortunately, current approaches fail to effectively guide models to attend to these diverse regions. To address this issue, this paper proposes a novel input transformation-based attack method, termed Component-Wise Transformation (CWT). CWT applies interpolation and selective rotation to individual image blocks, ensuring that each transformed image highlights different target regions, thereby improving the transferability of adversarial examples. Extensive experiments on the standard ImageNet dataset show that CWT consistently outperforms state-of-the-art methods in both attack success rates and stability across CNN- and Transformer-based models. |
| title | Enhancing Adversarial Transferability via Component-Wise Transformation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.11901 |