SAPD:面向遮挡人脸识别的对抗补丁分割防御方法OA

To address the issues of poor generalization and weak robustness against strong adversarial perturbations in existing face recognition defense methods against adversarial patches,a segmentation-based adversarial patch defense(SAPD)framework is proposed.In this method,a U-Net segmentation network fused with an attention mechanism is constructed,and a multi-scale hybrid loss function is em‑ployed to realize pixel-level patch localization.A morphological mask smoothing(MMS)strategy is in‑troduced to effectively remove perturbations while preserving facial structure.An occluded-area regu‑larization(OAR)loss function is further designed to improve occlusion robustness without adversarial training,maintaining clean-data accuracy.The experiments conducted on the LFW dataset with the added adversarial patches showed that the recognition accuracies of the method for the eyeglass-shaped patches,mask-shaped patch 1,and mask-shaped patch 2 reach 92.50%,96.16%,and 95.67%,respectively.Furthermore,consistent performance gains are observed across mainstream face recogni‑tion models such as MobileFaceNet,FaceNet,and IResNet50,verifying the strong compatibility,gener‑alization capability,and practical value of the proposed approach.