CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
This work addresses the need for efficient and balanced robustness evaluation in computer vision tasks like semantic segmentation and optical flow, though it is incremental as it builds on existing PGD methods.
The paper tackles the problem of evaluating neural network robustness in pixel-wise prediction tasks by proposing CosPGD, an adversarial attack that balances errors across the entire image domain while improving efficiency, outperforming previous state-of-the-art attacks on semantic segmentation.
While neural networks allow highly accurate predictions in many tasks, their lack of robustness towards even slight input perturbations often hampers their deployment. Adversarial attacks such as the seminal projected gradient descent (PGD) offer an effective means to evaluate a model's robustness and dedicated solutions have been proposed for attacks on semantic segmentation or optical flow estimation. While they attempt to increase the attack's efficiency, a further objective is to balance its effect, so that it acts on the entire image domain instead of isolated point-wise predictions. This often comes at the cost of optimization stability and thus efficiency. Here, we propose CosPGD, an attack that encourages more balanced errors over the entire image domain while increasing the attack's overall efficiency. To this end, CosPGD leverages a simple alignment score computed from any pixel-wise prediction and its target to scale the loss in a smooth and fully differentiable way. It leads to efficient evaluations of a model's robustness for semantic segmentation as well as regression models (such as optical flow, disparity estimation, or image restoration), and it allows it to outperform the previous SotA attack on semantic segmentation. We provide code for the CosPGD algorithm and example usage at https://github.com/shashankskagnihotri/cospgd.