Towards Understanding How Self-training Tolerates Data Backdoor
Poisoning

Towards Understanding How Self-training Tolerates Data Backdoor Poisoning

20 January 2023

Papers citing "Towards Understanding How Self-training Tolerates Data Backdoor Poisoning"

10 / 10 papers shown

Title
Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses Yuxin Yang Qiang Li Jinyuan Jia Yuan Hong Binghui Wang AAML FedML 49 10 0 12 Jul 2024
Purification Of Contaminated Convolutional Neural Networks Via Robust Recovery: An Approach with Theoretical Guarantee in One-Hidden-Layer Case Hanxiao Lu Zeyu Huang Ren Wang AAML 14 1 0 04 Jul 2024
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection Wei Li Pin-Yu Chen Sijia Liu Ren Wang AAML 41 2 0 09 Jun 2024
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency Soumyadeep Pal Yuguang Yao Ren Wang Bingquan Shen Sijia Liu AAML 34 8 0 15 Mar 2024
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free Tianlong Chen Zhenyu (Allen) Zhang Yihua Zhang Shiyu Chang Sijia Liu Zhangyang Wang AAML 44 25 0 24 May 2022
Combining Diverse Feature Priors Saachi Jain Dimitris Tsipras A. Madry 51 14 0 15 Oct 2021
Clean-Label Backdoor Attacks on Video Recognition Models Shihao Zhao Xingjun Ma Xiang Zheng James Bailey Jingjing Chen Yu-Gang Jiang AAML 185 252 0 06 Mar 2020
Confidence Regularized Self-Training Yang Zou Zhiding Yu Xiaofeng Liu B. Kumar Jinsong Wang 216 783 0 26 Aug 2019
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average Ben Athiwaratkun Marc Finzi Pavel Izmailov A. Wilson 191 243 0 14 Jun 2018
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results Antti Tarvainen Harri Valpola OOD MoMe 244 1,279 0 06 Mar 2017