.png){kind=icon}
返回
Uncertainty estimation based adversarial attack in multi-class classification
.png){kind=icon}
OA
AI
DOI：10.1007/s11042-022-13269-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Model uncertainty has gained popularity in machine learning due to the overconfident predictions derived from standard neural networks which are not trustworthy. Recently, Monte-Carlo based adversarial attack (MC-AA) has been proposed as a simple uncertainty estimation method which is powerful in capturing data points that lie in the overlapping distribution of the decision boundary. MC-AA produces uncertainties by performing back-and-forth perturbations of a given data point towards the decision boundary using the idea of adversarial attacks. Despite its efficacy against other uncertainty estimation methods, this method has been only examined on binary classification problems. Thus, we present and examine MC-AA with multi-class classification tasks. We point out the limitation of this method with multiple classes which we tackle by converting multiclass problem into 'one-versus-all' classification. We compare MC-AA against other recent model uncertainty methods on Cora - a graph structured dataset - and MNIST - an image dataset. Thus, the conducted experiments are performed using a variety of deep learning algorithms to perform the classification. Consequently, we discuss the best results of model uncertainty with Cora data using LEConv model of AUC-score 0.889 and MNIST data using CNN of AUC-score 0.98 against other uncertainty estimation methods.
Keyword:
Uncertainty estimation
Adversarial attack
Deep neural network
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
Chronic Pain and the Emotional Brain: Specific Brain Activity Associated with Spontaneous Fluctuations of Intensity of Chronic Back Pain慢性疼痛和情绪大脑: 与慢性背痛强度的自发性波动相关的特定大脑活动
OAAI
OAAI分享收藏Uncertainty estimation for stereo matching based on evidential deep learning基于证据深度学习的立体匹配不确定性估计.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Development and evaluation of FLEMOps – a new Flood Loss Estimation MOdel for the private sectorOAAI
OAAI分享收藏A review of uncertainty quantification in deep learning: Techniques, applications and challenges深度学习中的不确定性量化: 技术、应用与挑战INFORMATION FUSIONOAAI
INFORMATION FUSIONIF15.5
OAAI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PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Interleukin-2 Receptor Antagonists in Liver Transplantation: A Meta-analysis of Randomized Trials
PREAI
分享收藏
查看更多内容