A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models

Abstract: Patch robustness certification ensures no patch within a given bound on a sample can manipulate a deep learning model to predict a different label. However, existing techniques cannot certify samples that cannot meet their strict bars at the classifier or patch region levels. This paper proposes MajorCert. MajorCert firstly finds all possible label sets manipulatable by the same patch region on the same sample across the underlying classifiers, then enumerates their combinations element-wise, and finally checks whether the majority invariant of all these combinations is intact to certify samples.