MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908278195224576 |
|---|---|
| author | Zhang, Jiaming Qiu, Lingyu Yi, Qi Li, Yige Sang, Jitao Xu, Changsheng Yeung, Dit-Yan |
| author_facet | Zhang, Jiaming Qiu, Lingyu Yi, Qi Li, Yige Sang, Jitao Xu, Changsheng Yeung, Dit-Yan |
| contents | The vulnerability of Deep Neural Networks (DNNs) to adversarial attacks poses a significant challenge to their deployment in safety-critical applications. While extensive research has addressed various attack scenarios, the no-box attack setting where adversaries have no prior knowledge, including access to training data of the target model, remains relatively underexplored despite its practical relevance. This work presents a systematic investigation into leveraging large-scale Vision-Language Models (VLMs), particularly CLIP, as surrogate models for executing no-box attacks. Our theoretical and empirical analyses reveal a key limitation in the execution of no-box attacks stemming from insufficient discriminative capabilities for direct application of vanilla CLIP as a surrogate model. To address this limitation, we propose MF-CLIP: a novel framework that enhances CLIP's effectiveness as a surrogate model through margin-aware feature space optimization. Comprehensive evaluations across diverse architectures and datasets demonstrate that MF-CLIP substantially advances the state-of-the-art in no-box attacks, surpassing existing baselines by 15.23% on standard models and achieving a 9.52% improvement on adversarially trained models. Our code will be made publicly available to facilitate reproducibility and future research in this direction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_06608 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks Zhang, Jiaming Qiu, Lingyu Yi, Qi Li, Yige Sang, Jitao Xu, Changsheng Yeung, Dit-Yan Machine Learning Artificial Intelligence Cryptography and Security The vulnerability of Deep Neural Networks (DNNs) to adversarial attacks poses a significant challenge to their deployment in safety-critical applications. While extensive research has addressed various attack scenarios, the no-box attack setting where adversaries have no prior knowledge, including access to training data of the target model, remains relatively underexplored despite its practical relevance. This work presents a systematic investigation into leveraging large-scale Vision-Language Models (VLMs), particularly CLIP, as surrogate models for executing no-box attacks. Our theoretical and empirical analyses reveal a key limitation in the execution of no-box attacks stemming from insufficient discriminative capabilities for direct application of vanilla CLIP as a surrogate model. To address this limitation, we propose MF-CLIP: a novel framework that enhances CLIP's effectiveness as a surrogate model through margin-aware feature space optimization. Comprehensive evaluations across diverse architectures and datasets demonstrate that MF-CLIP substantially advances the state-of-the-art in no-box attacks, surpassing existing baselines by 15.23% on standard models and achieving a 9.52% improvement on adversarially trained models. Our code will be made publicly available to facilitate reproducibility and future research in this direction. |
| title | MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2307.06608 |