.png){kind=icon}
Return
Adversarial Attacks and Batch Normalization: A Batch Statistics Perspective
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3250661.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Batch Normalization (BatchNorm) is an effective architectural component in deep learning models that helps to improve model performance and speed up training. However, it has also been found to increase the vulnerability of models to adversarial attacks. In this study, we investigate the mechanism behind this vulnerability and took first steps towards a solution called RobustNorm. We observed that adversarial inputs tend to shift the distributions of the output of the BatchNorm layer, leading to inaccurate train-time statistics and increased vulnerability. Through a series of experiments on various architectures and datasets, we confirm our hypothesis. We also demonstrate the effectiveness of RobustNorm in improving the robustness of models under adversarial perturbation while maintaining the benefits of BatchNorm.
Keywords:
Batch production systems
Robustness
Feature extraction
Statistics
Adversarial machine learning
Neural networks
Transfer learning
Batch normalization
adversarial robustness
transfer learning
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
View more