Skip to main navigation Skip to search Skip to main content

Adversarially training for audio classifiers

  • École de technologie supérieure

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

9 Citations (Scopus)

Abstract

In this paper, we investigate the potential effect of the adversarially training on the robustness of six advanced deep neural networks against a variety of targeted and non-targeted adversarial attacks. We firstly show that, the ResNet-56 model trained on the 2D representation of the discrete wavelet transform appended with the tonnetz chromagram outperforms other models in terms of recognition accuracy. Then we demonstrate the positive impact of adversarially training on this model as well as other deep architectures against six types of attack algorithms (white and black-box) with the cost of the reduced recognition accuracy and limited adversarial perturbation. We run our experiments on two benchmarking environmental sound datasets and show that without any imposed limitations on the budget allocations for the adversary, the fooling rate of the adversarially trained models can exceed 90%. In other words, adversarial attacks exist in any scales, but they might require higher adversarial perturbations compared to non-adversarially trained models.

Original languageEnglish
Title of host publicationProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages9569-9576
Number of pages8
ISBN (Electronic)9781728188089
DOIs
Publication statusPublished - 2020
Event25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Online, Italy
Duration: 10 Jan 2021 → 15 Jan 2021

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference25th International Conference on Pattern Recognition, ICPR 2020
Country/TerritoryItaly
CityVirtual, Online
Period10/01/21 → 15/01/21

!!!Keywords

  • Adversarial attack
  • Adversarially training
  • AlexNet
  • Chromagram
  • Deep neural network
  • Discrete wavelet transformation (DWT)
  • GoogLeNet
  • ResNet
  • Short-Time Fourier Transformation (STFT)
  • Sound classification
  • Spectrogram
  • Tonnetz features
  • VGG

Fingerprint

Dive into the research topics of 'Adversarially training for audio classifiers'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this