.png){kind=icon}
返回
Adversarial Learning With Cost-Sensitive Classes
.png){kind=icon}
OA
AI
DOI：10.1109/TCYB.2022.3146388.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This article proposes a framework combining cost-sensitive classification and adversarial learning together to train a model that can distinguish between the protected and unprotected classes, such that the protected classes are less vulnerable to adversarial examples. We find in this framework an interesting phenomenon during the training of deep neural networks, called the Min-Max property, that is, the absolute values of most parameters in the convolutional layer approach 0 while the absolute values of a few parameters are significantly larger, becoming bigger. Based on this Min-Max property which is formulated and analyzed in a view of random distribution, we further build a new defense model against adversarial examples for adversarial robustness improvement. An advantage of the built model is that it performs better than the standard one and can combine with adversarial training to achieve improved performance. It is experimentally confirmed that, regarding the average accuracy of all classes, our model is almost as same as the existing models when an attack does not occur and is better than the existing models when an attack occurs. Specifically, regarding the accuracy of protected classes, the proposed model is much better than the existing models when an attack occurs.
Keyword:
Training
Robustness
Costs
Adversarial machine learning
Perturbation methods
Task analysis
Neural networks
Adversarial examples
adversarial training
attack and defense
cost sensitive
robustness
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
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Type II collagen–specific antibodies induce cartilage damage in mice independent of inflammation
PREAI
分享收藏Leveraging Long and Short-Term Information in Content-Aware Movie Recommendation via Adversarial Training通过对抗性训练在内容感知的电影推荐中利用长期和短期信息
PREAI
分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容