Proximal Splitting Adversarial Attacks for Semantic Segmentation
This provides a more accurate adversarial benchmark for semantic segmentation, a dense prediction task where attacks were previously understudied.
The paper tackles the problem of generating adversarial attacks for semantic segmentation models, showing that existing methods overestimate perturbation sizes. Their proximal splitting attack produces perturbations with much smaller ℓ∞ norms and significantly outperforms previous approaches.
Classification has been the focal point of research on adversarial attacks, but only a few works investigate methods suited to denser prediction tasks, such as semantic segmentation. The methods proposed in these works do not accurately solve the adversarial segmentation problem and, therefore, overestimate the size of the perturbations required to fool models. Here, we propose a white-box attack for these models based on a proximal splitting to produce adversarial perturbations with much smaller $\ell_\infty$ norms. Our attack can handle large numbers of constraints within a nonconvex minimization framework via an Augmented Lagrangian approach, coupled with adaptive constraint scaling and masking strategies. We demonstrate that our attack significantly outperforms previously proposed ones, as well as classification attacks that we adapted for segmentation, providing a first comprehensive benchmark for this dense task.