PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing. (arXiv:2111.10481v2 [cs.CV] UPDATED)

Vision Transformer (ViT) is known to be highly nonlinear like other classical
neural networks and could be easily fooled by both natural and adversarial
patch perturbations. This limitation could pose a threat to the deployment of
ViT in the real industrial environment, especially in safety-critical
scenarios. In this work, we propose PatchCensor, aiming to certify the patch
robustness of ViT by applying exhaustive testing. We try to provide a provable
guarantee by considering the worst patch attack scenarios. Unlike empirical …

adversarial attack certification critical deployment environment guarantee industrial may networks neural networks patch patches robustness safety safety-critical testing threat transformers work