Search Results for author: Qilin Zhou

Found 2 papers, 1 papers with code

CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models

no code implementations • 13 May 2024 • Qilin Zhou, Zhengyuan Wei, Haipeng Wang, Bo Jiang, W. K. Chan

CrossCert formulates a novel approach by cross-checking two certified recovery defenders to provide unwavering certification and detection certification.

Paper
Add Code

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

1 code implementation • 1 Aug 2023 • Qilin Zhou, Zhengyuan Wei, Haipeng Wang, W. K. Chan

Patch robustness certification ensures no patch within a given bound on a sample can manipulate a deep learning model to predict a different label.

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.