MRCert: תואר רשמי לאיוש פוסט-הפצה של תואר רשמי לאיוש פוסט-הפצה

תקציר מקורי באנגליתarXiv:2610.10617v1 Announce Type: cross Abstract: 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 achieve both simultaneously: they degrade the prediction accuracy much and cannot verify the benignity of the returned label of an adversarially patched input, respectively. We propose MRCert, the first masking-based certified recovery defender that shows the feasibility of achieving both. Unlike all existing works to apply a common condition across both types of input (benign and adversarially patched samples) for certificatio