期刊
MULTIMEDIA TOOLS AND APPLICATIONS
卷 78, 期 3, 页码 2815-2835出版社
SPRINGER
DOI: 10.1007/s11042-018-5853-4
关键词
Adversarial images detection; Deep convolutional neural network; Machine learning security
类别
资金
- Smart News, Social sensing for breaking news
- Tuscany region under the FAR-FAS 2014 program [CUP CIPE D58C15000270008]
- Fondazione Cassa di Risparmio di Firenze (Italy)
- NVIDIA Corporation
Deep neural networks are more and more pervading many computer vision applications and in particular image classification. Notwithstanding that, recent works have demonstrated that it is quite easy to create adversarial examples, i.e., images malevolently modified to cause deep neural networks to fail. Such images contain changes unnoticeable to the human eye but sufficient to mislead the network. This represents a serious threat for machine learning methods. In this paper, we investigate the robustness of the representations learned by the fooled neural network, analyzing the activations of its hidden layers. Specifically, we tested scoring approaches used for kNN classification, in order to distinguish between correctly classified authentic images and adversarial examples. These scores are obtained searching only between the very same images used for training the network. The results show that hidden layers activations can be used to reveal incorrect classifications caused by adversarial attacks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据