Multi-Targeted Backdoor: Indentifying Backdoor Attack for Multiple Deep Neural Networks

Cited 11 time in webofscience Cited 0 time in scopus
  • Hit : 289
  • Download : 0
We propose a multi-targeted backdoor that misleads different models to different classes. The method trains multiple models with data that include specific triggers that will be misclassified by different models into different classes. For example, an attacker can use a single multi-targeted backdoor sample to make model A recognize it as a stop sign, model B as a left-turn sign, model C as a right-turn sign, and model D as a U-turn sign. We used MNIST and Fashion-MNIST as experimental datasets and Tensorflow as a machine learning library. Experimental results show that the proposed method with a trigger can cause misclassification as different classes by different models with a 100% attack success rate on MNIST and Fashion-MNIST while maintaining the 97.18% and 91.1% accuracy, respectively, on data without a trigger.
Publisher
IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
Issue Date
2020-04
Language
English
Article Type
Article
Citation

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E103D, no.4

ISSN
1745-1361
DOI
10.1587/transinf.2019edl8170
URI
http://hdl.handle.net/10203/274290
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 11 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0