Fooling End-To-End Speaker Verification With Adversarial Examples

Обман сквозной системы верификации диктора с помощью состязательных примеров
Moustapha Cissé, Joseph Keshet, Yossi Adi, Felix Kreuk
2018-04-01

adversarial examplesblack-box attacksend-to-end deep neural networksspeaker verificationwhite-box attacks
Automatic speaker verification systems are increasingly used as the primary means to authenticate costumers. Recently, it has been proposed to train speaker verification systems using end-to-end deep neural models. In this paper, we show that such systems are vulnerable to adversarial example attacks. Adversarial examples are generated by adding a peculiar noise to original speaker examples, in such a way that they are almost indistinguishable, by a human listener. Yet, the generated waveforms, which sound as speaker A can be used to fool such a system by claiming as if the waveforms were uttered by speaker B. We present white-box attacks on a deep end-to-end network that was either trained on YOHO or NTIMIT. We also present two black-box attacks. In the first one, we generate adversarial examples with a system trained on NTIMIT and perform the attack on a system that trained on YOHO. In the second one, we generate the adversarial examples with a system trained using Mel-spectrum features and perform the attack on a system trained using MFCCs. Our results show that one can significantly decrease the accuracy of a target system even when the adversarial examples are generated with different system potentially using different features.
1
Adversarial waveforms sounding like speaker A can cause verification systems to accept them as being spoken by speaker B.
2
Attack effectiveness transfers across feature representations: examples generated using Mel-spectrum features can significantly reduce accuracy in systems using MFCCs.
3
Black-box attacks transfer across systems trained on different datasets, including adversarial examples generated on NTIMIT and tested against YOHO-trained systems.
4
End-to-end deep speaker-verification systems are vulnerable to adversarial examples that remain nearly indistinguishable from original speech to human listeners.
5
White-box attacks successfully target end-to-end networks trained on either YOHO or NTIMIT datasets.

end-to-end deep neural speaker verification systems

vulnerability of speaker verification systems to adversarial example attacks, including attack transferability across training datasets, models, and acoustic features

Publication Details
Publication Date
2018-04-01
Journal
Publisher
ISSN
Cited by
181
Access Type
Author Information
Authors
Moustapha Cissé
Joseph Keshet
Yossi Adi
Felix Kreuk
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%