.png){kind=icon}
返回
Hyperspherical class prototypes for adversarial robustness
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108527.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This work addresses the problem of adversarial robustness in deep neural network classification from an optimal class boundary estimation perspective. It is argued that increased model robustness to adversarial attacks can be achieved when the feature learning process is monitored by geometrically-inspired opti-mization criteria. To this end, we propose to learn hyperspherical class prototypes in the neural feature embedding space, along with training the network parameters. Three concurrent optimization functions for the intermediate hidden layer training data activations are devised, requiring items of the same class to be enclosed by the corresponding class prototype boundaries, to have minimum distance from their class prototype vector (i.e., hypersphere center) and to have maximum distance from the remainder hy-persphere centers. Our experiments show that training standard classification model architectures with the proposed objectives, significantly increases their robustness to white-box adversarial attacks, without adverse (if not beneficial) effects to their classification accuracy. (c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Adversarial defense
Adversarial robustness
Hypersphere prototype loss
HCP loss
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
K-Anonymity inspired adversarial attack and multiple one-class classification defense.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Surrogate network-based sparseness hyper-parameter optimization for deep expression recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Semi-supervised subclass support vector data description for image and video classificationNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Cost-conscious comparison of supervised learning algorithms over multiple data setsPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容