Advanced Ensemble Adversarial Example on Unknown Deep Neural Network Classifiers

Cited 3 time in webofscience Cited 0 time in scopus
  • Hit : 111
  • Download : 0
Deep neural networks (DNNs) are widely used in many applications such as image, voice, and pattern recognition. However, it has recently been shown that a DNN can be vulnerable to a small distortion in images that humans cannot distinguish. This type of attack is known as an adversarial example and is a significant threat to deep learning systems. The unknown-target-oriented generalized adversarial example that can deceive most DNN classifiers is even more threatening. We propose a generalized adversarial example attack method that can effectively attack unknown classifiers by using a hierarchical ensemble method. Our proposed scheme creates advanced ensemble adversarial examples to achieve reasonable attack success rates for unknown classifiers. Our experiment results show that the proposed method can achieve attack success rates for an unknown classifier of up to 9.25% and 18.94% higher on MNIST data and 4.1% and 13% higher on CIFAR10 data compared with the previous ensemble method and the conventional baseline method, respectively.
Publisher
IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
Issue Date
2018-10
Language
English
Article Type
Article
Citation

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E101D, no.10, pp.2485 - 2500

ISSN
1745-1361
DOI
10.1587/transinf.2018EDP7073
URI
http://hdl.handle.net/10203/246212
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 3 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0