A Generative Victim Model for Segmentation
This work addresses adversarial attack generation for segmentation, offering a novel approach that could impact security in computer vision, though it appears incremental in the broader field of adversarial attacks.
The paper tackles the problem of generating adversarial attacks for segmentation tasks by proposing a generative victim model that does not require explicit segmentation models, achieving effective attacks with good transferability.
We find that the well-trained victim models (VMs), against which the attacks are generated, serve as fundamental prerequisites for adversarial attacks, i.e. a segmentation VM is needed to generate attacks for segmentation. In this context, the victim model is assumed to be robust to achieve effective adversarial perturbation generation. Instead of focusing on improving the robustness of the task-specific victim models, we shift our attention to image generation. From an image generation perspective, we derive a novel VM for segmentation, aiming to generate adversarial perturbations for segmentation tasks without requiring models explicitly designed for image segmentation. Our approach to adversarial attack generation diverges from conventional white-box or black-box attacks, offering a fresh outlook on adversarial attack strategies. Experiments show that our attack method is able to generate effective adversarial attacks with good transferability.