Robust Audio Adversarial Example for a Physical Attack
1.
2.
Goodfellow, I. J., Shlens, J., & Szegedy, C.: Explaining and harnessing adversarial examples. In Proc. of ICLR. (2015)
3.
Carlini, N., & Wagner, D.: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In Proc. of Deep Learning and Security Workshop. (2018)
4.
Carlini, N., & Wagner, D.: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In Proc. of Deep Learning and Security Workshop. (2018)
5.
f :Rn
→ {1,…,k}
x ∈!n
!x ∈"n
s.t. f (x) ≠ f (!x) ∧ D(x, !x) ≤ δ
!x s.t. f (!x) = l ∧ D(x, !x) ≤ δ
l ∈{1,…,k}
panda
f
gibbon
x
!x
f (x)
f (!x)
6.
!x = x + !v where !v = argmin
v
Loss
f
(x + v,l)+ ε " v "
ε D(x, !x) ≤ δ
panda
7.
!x = x + !v where !v = argmin
v
Loss
f
(x + v,l)+ ε " v "
ε D(x, !x) ≤ δ
gibbon
8. Athalye, A., et. al.: Synthesizing robust adversarial examples. In Proc. of ICML. (2018)
f (!x) = l
9.
argmin
v
Et~Τ Loss
f
(t(x + v),l)+ ε D(t(x),t(x + v))⎡
⎣⎢
⎤
⎦⎥
argmin
v
Loss
f
(x + v,l)+ ε ! v !
Athalye, A., et. al.: Synthesizing robust adversarial examples. In Proc. of ICML. (2018)
10. Yuan, X., et. al.: CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition. In Proc. of USENIX Security. (2018)
Carlini, N., & Wagner, D.: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In Proc. of Deep Learning and Security Workshop. (2018)
11.
Yuan, X., et. al.: CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition. In Proc. of USENIX Security. (2018)
Carlini, N., & Wagner, D.: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In Proc. of Deep Learning and Security Workshop. (2018)
12.
Yuan, X., et. al.: CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition. In Proc. of USENIX Security. (2018)
Carlini, N., & Wagner, D.: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In Proc. of Deep Learning and Security Workshop. (2018)
13.
argmin
v
Loss
f
(MFCC(x + v), l)+ ε ! v !
x ∈!T
l ∈∑N
argmin
v
Loss
f
(x + v,l)+ ε ! v !
Carlini, N., & Wagner, D.: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In Proc. of Deep Learning and Security Workshop. (2018)
14.
Carlini, N., & Wagner, D.: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In Proc. of Deep Learning and Security Workshop. (2018)
Loss vt
15.
Athalye, A., et. al.: Synthesizing robust adversarial examples. In Proc. of ICML. (2018)
20.
x
Carlini, N., & Wagner, D.: Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. In Proc. of Deep Learning and Security Workshop. (2018)
Hannun, A. Y., et. al.: Deep Speech: Scaling up end- to-end speech recognition. arXiv preprint arXiv:1412.05567. (2014)
36.
Schönherr, L., et. al.: Adversarial Attacks Against ASR Systems via Psychoacoustic Hiding. In Proc. of NDSS. (2019)
Yuan, X., et. al.: CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition. In Proc. of USENIX Security. (2018)
37.
Taori, R., et. al.: Targeted Adversarial Examples for Black Box Audio Systems. arXiv preprint arXiv:1805.07820. (2018)