Art

J-GLOBAL ID：202002246715013515   Reference number：20A0407281

GENERATION OF ADVERSARIAL EXAMPLES USING ADAPTIVE DIFFERENTIAL EVOLUTION

適応微分進化を用いた敵対的事例の生成

Author (3)： KUSHIDA Jun-ichi (Hiroshima City Univ., Hiroshima-shi, JPN) ,  HARA Akira (Hiroshima City Univ., Hiroshima-shi, JPN) ,  TAKAHAMA Tetsuyuki (Hiroshima City Univ., Hiroshima-shi, JPN)
Material： International Journal of Innovative Computing, Information and Control  (IJICIC)
Volume： 16  Issue： 1  Page： 405-414  Publication year： Feb. 2020 
JST Material Number： F1199A  ISSN： 1349-4198  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *evolutionary computation ,  *optimization method ,  *neural network(biomodel) ,  neural network(network) ,  perturbation ,  black box ,  model
Semi thesaurus term： *deep neural network ,  internal model ,  *differential evolution

JST classification (2)： Computer networks  (JC03000K) ,  Computer simulation  (JE11000H)

Reference (18)：

• A. Krizhevsky, I. Sutskever and G. E. Hinton, Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, pp.1097-1105, 2012.
• C. Liu, F. Liu, L. Wang, L. Ma and Z.-M. Lu, Segmentation of nerve on ultrasound images using deep adversarial network, International Journal of Innovative Computing, Information and Control, vol.14, no.1, pp.53-64, 2018.
• I. M. Kamal, H. Bae, S. Sim, H. Kim, D. Kim, Y. Choi and H. Yun, Forecasting high-dimensional multivariate regression of Baltic Dry Index (BDI) using Deep Neural Networks (DNN), ICIC Express Letters, vol.13, no.5, pp.427-434, 2019.
• S. Moosavi-Dezfooli, A. Fawzi and P. Frossard, Deepfool: A simple and accurate method to fool deep neural networks, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2574-2582, 2016.
• N. Papernot, P. McDaniel, S. Jha, M. Fredrikson, Z. B. Celik and A. Swami, The limitations of deep learning in adversarial settings, The 1st IEEE European Symposium on Security and Privacy (EuroS&P), Saarbrucken, Germany, pp.372-387, 2016.

Terms in the title (3)： 適応 ,  微分進化 ,  敵対