Journal
IEEE SIGNAL PROCESSING LETTERS
Volume 29, Issue -, Pages 1432-1436Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2022.3183538
Keywords
Perturbation methods; Distortion; Speaker recognition; Computational modeling; Signal processing algorithms; Task analysis; Time-domain analysis; Adversarial example; decision-based attack; speaker recognition system
Categories
Funding
- National Natural Science Foundation of China [6217011361, 61901237]
- Zhejiang Natural Science Foundation [LY20F020010]
- Ningbo Natural Science Foundation [202003N4089]
- Alibaba Innovative Research Program
- K.C. Wong Magna Fund in Ningbo University
Ask authors/readers for more resources
This letter proposes a two-step query-efficient decision-based attack based on local low-frequency perturbation for speaker recognition systems, which achieves a higher attacking success rate.
Despite neural network-based speaker recognition systems (SRS) have enjoyed significant success, they are proved to be quite vulnerable to adversarial examples. In practice, the SRS model parameters are not always available. Attackers have to probe the model only via querying, and such decision-based attacking merely relies on the output label is quite challenging. This letter proposes a two-step query-efficient decision-based attack based on local low-frequency perturbation. Specifically, instead of imposing perturbation on the entire audio sample, a local attacking region is firstly sought, confining the perturbed distortion to a local region. Second, considering that the majority of energy concentrates on the low-frequency bands, the proposed method suggests performing perturbation generation in the low-frequency domain. Experimental results demonstrate that, compared with the recent methods, our method could implement target attacking to SRS with a higher attacking success rate, at the cost of much lower queries and adversarial perturbation.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available