Art
J-GLOBAL ID:202102270719644629   Reference number:21A1260978

Detection of Adversarial Examples in CNN Image Classifiers Using Features Extracted with Multiple Strengths of Filter

複数のフィルタ強度によるCNN画像分類器の応答特性を用いた敵対的事例の検出法
Author (5):
Material:
Volume: 120  Issue: 418(EMM2020 67-79)  Page: 19-24 (WEB ONLY)  Publication year: Feb. 25, 2021 
JST Material Number: U2030A  ISSN: 2432-6380  Document type: Proceedings
Article type: 原著論文  Country of issue: Japan (JPN)  Language: JAPANESE (JA)
Thesaurus term:
Thesaurus term/Semi thesaurus term
Keywords indexed to the article.
All keywords is available on JDreamIII(charged).
On J-GLOBAL, this item will be available after more than half a year after the record posted. In addtion, medical articles require to login to MyJ-GLOBAL.

Semi thesaurus term:
Thesaurus term/Semi thesaurus term
Keywords indexed to the article.
All keywords is available on JDreamIII(charged).
On J-GLOBAL, this item will be available after more than half a year after the record posted. In addtion, medical articles require to login to MyJ-GLOBAL.

JST classification (1):
JST classification
Category name(code) classified by JST.
Pattern recognition 
Reference (19):
  • K. Grosse, P. Manoharan, N. Papernot, M. Backes, and P. McDaniel, On the (statistical) detection of adversarial examples, 2017.
  • X. Li and F. Li, “Adversarial examples detection in deep networks with convolutional filter statistics,” in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5764-5772.
  • Z. Gong, W. Wang, and W. Ku, “Adversarial and clean data are not twins,” ArXiv, vol. abs/1704.04960, 2017.
  • J. H. Metzen, T. Genewein, V. Fischer, and B. Bischoff, “On detecting adversarial perturbations,” in Proc. ICLR, 2017.
  • W. Xu, D. Evans, and Y. Qi, “Feature squeezing: detecting adversarial examples in deep neural networks,” in Proc. NDSS2018, 2018.
more...
Terms in the title (5):
Terms in the title
Keywords automatically extracted from the title.

Return to Previous Page