On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models
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_ | 1866917767037321216 |
|---|---|
| author | Malik, Hashmat Shadab Saeed, Numan Hanif, Asif Naseer, Muzammal Yaqub, Mohammad Khan, Salman Khan, Fahad Shahbaz |
| author_facet | Malik, Hashmat Shadab Saeed, Numan Hanif, Asif Naseer, Muzammal Yaqub, Mohammad Khan, Salman Khan, Fahad Shahbaz |
| contents | Volumetric medical segmentation models have achieved significant success on organ and tumor-based segmentation tasks in recent years. However, their vulnerability to adversarial attacks remains largely unexplored, raising serious concerns regarding the real-world deployment of tools employing such models in the healthcare sector. This underscores the importance of investigating the robustness of existing models. In this context, our work aims to empirically examine the adversarial robustness across current volumetric segmentation architectures, encompassing Convolutional, Transformer, and Mamba-based models. We extend this investigation across four volumetric segmentation datasets, evaluating robustness under both white box and black box adversarial attacks. Overall, we observe that while both pixel and frequency-based attacks perform reasonably well under \emph{white box} setting, the latter performs significantly better under transfer-based black box attacks. Across our experiments, we observe transformer-based models show higher robustness than convolution-based models with Mamba-based models being the most vulnerable. Additionally, we show that large-scale training of volumetric segmentation models improves the model's robustness against adversarial attacks. The code and robust models are available at https://github.com/HashmatShadab/Robustness-of-Volumetric-Medical-Segmentation-Models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08486 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models Malik, Hashmat Shadab Saeed, Numan Hanif, Asif Naseer, Muzammal Yaqub, Mohammad Khan, Salman Khan, Fahad Shahbaz Image and Video Processing Computer Vision and Pattern Recognition Volumetric medical segmentation models have achieved significant success on organ and tumor-based segmentation tasks in recent years. However, their vulnerability to adversarial attacks remains largely unexplored, raising serious concerns regarding the real-world deployment of tools employing such models in the healthcare sector. This underscores the importance of investigating the robustness of existing models. In this context, our work aims to empirically examine the adversarial robustness across current volumetric segmentation architectures, encompassing Convolutional, Transformer, and Mamba-based models. We extend this investigation across four volumetric segmentation datasets, evaluating robustness under both white box and black box adversarial attacks. Overall, we observe that while both pixel and frequency-based attacks perform reasonably well under \emph{white box} setting, the latter performs significantly better under transfer-based black box attacks. Across our experiments, we observe transformer-based models show higher robustness than convolution-based models with Mamba-based models being the most vulnerable. Additionally, we show that large-scale training of volumetric segmentation models improves the model's robustness against adversarial attacks. The code and robust models are available at https://github.com/HashmatShadab/Robustness-of-Volumetric-Medical-Segmentation-Models. |
| title | On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.08486 |