ResearchTrend.AI
Purification Of Contaminated Convolutional Neural Networks Via Robust Recovery: An Approach with Theoretical Guarantee in One-Hidden-Layer Case

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
ArXivPDFHTML

Papers citing "Purification Of Contaminated Convolutional Neural Networks Via Robust Recovery: An Approach with Theoretical Guarantee in One-Hidden-Layer Case"

3 / 3 papers shown
Title
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
Wei Li
Pin-Yu Chen
Sijia Liu
Ren Wang
AAML
51
3
0
09 Jun 2024
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
Soumyadeep Pal
Yuguang Yao
Ren Wang
Bingquan Shen
Sijia Liu
AAML
41
8
0
15 Mar 2024
Denoising Noisy Neural Networks: A Bayesian Approach with Compensation
Denoising Noisy Neural Networks: A Bayesian Approach with Compensation
Yulin Shao
Soung Chang Liew
Deniz Gunduz
61
14
0
22 May 2021