首页|New Findings from Institute of Information Technology Update Understanding of Machine Learning (Ma-cat: Misclassification-aware Contrastive Adversarial Training)
New Findings from Institute of Information Technology Update Understanding of Machine Learning (Ma-cat: Misclassification-aware Contrastive Adversarial Training)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Wiley
Investigators publish new report on Machine Learning. According to news reporting out of Zhengzhou, People’s Republic of China, by NewsRx editors, research stated, “Vulnerability to adversarial examples poses a significant challenge to the secure application of deep neural networks. Adversarial training and its variants have shown great potential in addressing this problem.” Financial supporters for this research include Song Shan Laboratory, Program of Song Shan Laboratory (Included in the management of the Major Science and Technology Program of Henan Province). Our news journalists obtained a quote from the research from the Institute of Information Technology, “However, such approaches, which directly optimize the decision boundary, often result in overly complex adversarial decision boundaries that are detrimental to generalization. To deal with this issue, a novel plug-and-play method known as Misclassification-Aware Contrastive Adversarial Training (MA-CAT) from the perspective of data distribution optimization is proposed. MA-CAT leverages supervised decoupled contrastive learning to cluster nature examples within the same class in the logit space, indirectly increasing the margins of examples. Moreover, by taking into account the varying difficulty levels of adversarial training for different examples, MA-CAT adaptively customizes the strength of adversarial training for each example using an instance-wise misclassification-aware adaptive temperature coefficient.”
ZhengzhouPeople’s Republic of ChinaAsiaMachine LearningInstitute of Information Technology
NETL
NSTL
Wiley
