BriefGPT.xyz
Aug, 2023
深度学习模型修复稳定性认证的多数不变方法
A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models
HTML
PDF
Qilin Zhou, Zhengyuan Wei, Haipeng Wang, W. K. Chan
TL;DR
使用MajorCert方法，该研究论文提出了一种修补程序鲁棒性认证技术，可以确保在一个样本中，没有任何修补程序能够操纵深度学习模型以预测不同的标签。
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
→