Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation. (arXiv:2209.05980v1 [cs.CV])

Web: http://arxiv.org/abs/2209.05980

Adversarial patch attacks are an emerging security threat for real world deep
learning applications. We present Demasked Smoothing, the first approach (up to
our knowledge) to certify the robustness of semantic segmentation models
against this threat model. Previous work on certifiably defending against patch
attacks has mostly focused on image classification task and often required
changes in the model architecture and additional training which is undesirable
and computationally expensive. In Demasked Smoothing, any segmentation model
can be applied without particular …

adversarial attacks certified patch segmentation