Efficient Certified Defenses Against Patch Attacks on Image Classifiers

8 February 2021

Papers citing "Efficient Certified Defenses Against Patch Attacks on Image Classifiers"

8 / 8 papers shown

Title
CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models Qili Zhou Zhengyuan Wei Haipeng Wang Bo Jiang William Chan AAML 45 1 0 13 May 2024
PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses Chong Xiang Tong Wu Sihui Dai Jonathan Petit Suman Jana Prateek Mittal 54 3 0 19 Oct 2023
A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models Qili Zhou Zhengyuan Wei Haipeng Wang William Chan AAML 38 0 0 01 Aug 2023
Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey Abhijith Sharma Yijun Bian Phil Munz Apurva Narayan VLM AAML 38 20 0 16 Jun 2022
Towards Practical Certifiable Patch Defense with Vision Transformer Zhaoyu Chen Yue Liu Jianghe Xu Shuang Wu Shouhong Ding Wenqiang Zhang AAML ViT 40 66 0 16 Mar 2022
PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier Chong Xiang Saeed Mahloujifar Prateek Mittal VLM AAML 24 74 0 20 Aug 2021
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning Jinyuan Jia Yupei Liu Neil Zhenqiang Gong SILM SSL 47 152 0 01 Aug 2021
Safety Verification of Deep Neural Networks Xiaowei Huang Marta Kwiatkowska Sen Wang Min Wu AAML 183 932 0 21 Oct 2016