Acoustic-decoy: Detection of adversarial examples through audio modification on speech recognition system

Cited 12 time in webofscience Cited 0 time in scopus
  • Hit : 165
  • Download : 49
Deep neural networks (DNNs) display good performance in the domains of recognition and prediction, such as on tasks of image recognition, speech recognition, video recognition, and pattern analysis. However, adversarial examples, created by inserting a small amount of noise into the original samples, can be a serious threat because they can cause misclassification by the DNN. Adversarial examples have been studied primarily in the context of images, but their effect in the audio context is now drawing considerable interest as well. For example, by adding a small distortion to an original audio sample, imperceptible to humans, an audio adversarial example can be created that humans hear as error-free but that causes misunderstanding by a machine. Therefore, it is necessary to create a method of defense for resisting audio adversarial examples. In this paper, we propose an acoustic-decoy method for detecting audio adversarial examples. Its key feature is that it adds well-formalized distortions using audio modification that are sufficient to change the classification result of an adversarial example but do not affect the classification result of an original sample. Experimental results show that the proposed scheme can detect adversarial examples by reducing the similarity rate for an adversarial example to 6.21%, 1.27%, and 0.66% using low-pass filtering (with 12 dB roll-off), 8-bit reduction, and audio silence removal techniques, respectively. It can detect an audio adversarial example with a success rate of 97% by performing a comparison with the initial audio sample.
Publisher
ELSEVIER
Issue Date
2020-12
Language
English
Article Type
Article
Citation

NEUROCOMPUTING, v.417, pp.357 - 370

ISSN
0925-2312
DOI
10.1016/j.neucom.2020.07.101
URI
http://hdl.handle.net/10203/279430
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
Acoustic-decoy- Detection of adversarial examples through audio modific 복사본.pdf(5.09 MB)Download
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 12 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0