.png){kind=icon}
返回
Adversarial Attacks and Batch Normalization: A Batch Statistics Perspective
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3250661.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
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.
Keyword:
Batch production systems
Robustness
Feature extraction
Statistics
Adversarial machine learning
Neural networks
Transfer learning
Batch normalization
adversarial robustness
transfer learning
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
ARVino - outdoor augmented reality visualisation of viticulture GIS dataARVino-葡萄栽培GIS数据的户外增强现实可视化
OAAI
.png){kind=icon}
OAAI分享收藏Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容