Toward Intelligent Detection Modelling for Adversarial Samples in Convolutional Neural Networks

Zhuobiao Qiao, Mianxiong Dong, Kaoru Ota, Jun Wu

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

Deep Neural Networks (DNNs) are hierarchical nonlinear architectures that have been widely used in artificial intelligence applications. However, these models are vulnerable to adversarial perturbations which add changes slightly and are crafted explicitly to fool the model. Such attacks will cause the neural network to completely change its classification of data. Although various defense strategies have been proposed, existing defense methods have two limitations. First, the discovery success rate is not very high. Second, existing methods depend on the output of a particular layer in a specific learning structure. In this paper, we propose a powerful method for adversarial samples using Large Margin Cosine Estimate(LMCE). By iteratively calculating the large-margin cosine uncertainty estimates between the model predictions, the results can be regarded as a novel measurement of model uncertainty estimation and is available to detect adversarial samples by training using a simple machine learning algorithm. Comparing it with the way in which adversar- ial samples are generated, it is confirmed that this measurement can better distinguish hostile disturbances. We modeled deep neural network attacks and established defense mechanisms against various types of adversarial attacks. Classifier gets better performance than the baseline model. The approach is validated on a series of standard datasets including MNIST and CIFAR -10, outperforming previous ensemble method with strong statistical significance. Experiments indicate that our approach generalizes better across different architectures and attacks.

本文言語English
ホスト出版物のタイトル2018 IEEE 23rd International Workshop on Computer Aided Modeling and Design of Communication Links and Networks, CAMAD 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781538661512
DOI
出版ステータスPublished - 2018 10 29
外部発表はい
イベント23rd IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks, CAMAD 2018 - Barcelona, Spain
継続期間: 2018 9 172018 9 19

出版物シリーズ

名前IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks, CAMAD
2018-September
ISSN(電子版)2378-4873

Conference

Conference23rd IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks, CAMAD 2018
国/地域Spain
CityBarcelona
Period18/9/1718/9/19

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • コンピュータ グラフィックスおよびコンピュータ支援設計

フィンガープリント

「Toward Intelligent Detection Modelling for Adversarial Samples in Convolutional Neural Networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル