arXiv cs.AI· Qilin Zhou, Zhengyuan Wei, Haipeng Wang, Zhuo Wang, Shuo Liu, W. K. Chan·· 9 天前AI 评分22
MRCert：面向对抗补丁样本的部署后补丁鲁棒性认证
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
AI 导读
研究者提出 MRCert，首个基于掩码的认证式恢复防御方法，可同时保持高预测准确率并验证对抗补丁样本返回标签的良性。它针对良性样本与对抗补丁样本分别推断类型特定的模型必要属性，并通过类型导向的标签恢复与认证函数对进行形式化验证。在 ImageNet、16 像素补丁下，MRCert 取得 35.1% 对抗认证准确率，而 SOTA 方法 PatchCURE 完全失效。
正文 · 原文
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 certification, MRCert infers type-specific necessary properties of deep learning models for both types in post-deployment time and formally relates them to verify the label benignity through a novel type-oriented design of label recovery and certification function pair. Without incurring the degradation in clean accuracy caused by smoothing, experimental results confirm that MRCert achieves 35.1\% adversarial certified accuracy on ImageNet at patch size 16 pixels, whereas the SOTA PatchCURE fails completely.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.10617 [cs.CR] |
| (or arXiv:2610.10617v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10617 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qilin Zhou [view email]
[v1]
Wed, 7 Oct 2026 07:27:16 UTC (289 KB)
来源：arXiv cs.AI · arxiv.org