Pseudo-Siamese Network based Timbre-reserved Black-box Adversarial Attack in Speaker Identification

Qing Wang, Jixun Yao, Ziqian Wang, Pengcheng Guo, Lei Xie

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

In this study, we propose a timbre-reserved adversarial attack approach for speaker identification (SID) to not only exploit the weakness of the SID model but also preserve the timbre of the target speaker in a black-box attack setting. Particularly, we generate timbre-reserved fake audio by adding an adversarial constraint during the training of the voice conversion model. Then, we leverage a pseudo-Siamese network architecture to learn from the black-box SID model constraining both intrinsic similarity and structural similarity simultaneously. The intrinsic similarity loss is to learn an intrinsic invariance, while the structural similarity loss is to ensure that the substitute SID model shares a similar decision boundary to the fixed black-box SID model. The substitute model can be used as a proxy to generate timbre-reserved fake audio for attacking. Experimental results on the Audio Deepfake Detection (ADD) challenge dataset indicate that the attack success rate of our proposed approach yields up to 60.58% and 55.38% in the white-box and black-box scenarios, respectively, and can deceive both human beings and machines.

Original languageEnglish
Pages (from-to)3994-3998
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2023-August
DOIs
StatePublished - 2023
Event24th International Speech Communication Association, Interspeech 2023 - Dublin, Ireland
Duration: 20 Aug 202324 Aug 2023

Keywords

  • adversarial attack
  • black-box
  • speaker identification
  • timbre-reserved

Fingerprint

Dive into the research topics of 'Pseudo-Siamese Network based Timbre-reserved Black-box Adversarial Attack in Speaker Identification'. Together they form a unique fingerprint.

Cite this