Preprint Open access
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certification on such inputs within a patch bound can verify their label benignity and should retain high prediction accuracy. However, existing smoothing-based and masking-based recovery defenders cannot a …