A Square Attack test was performed on
swinv2-large-patch4-window12to16-192to256-22kto1k-ft, in which
a 40% failure rate was observed.
In at least one case, the model's prediction changed -0.51. This caused the label to change from 803 to 915.
This test measures the robustness of the model to Square attacks. It does this by taking a sample input, applying a Square attack, and measuring the performance of the model on the perturbed input. See the paper "Square Attack: a query-efficient black-box adversarial attack via random search" by Andriushchenko, Croce, et al. (https://arxiv.org/abs/1912.00049) for more details.
Malicious actors can perturb input images to alter model behavior in unexpected ways. It is important that Computer Vision models are robust to such attacks.
This report was automatically generated by the scanning engine
rime-0.21.0rc4.post195+git.2a88076b.d on 2023-01-12 17:49.