FOOLHD: FOOLING SPEAKER IDENTIFICATION BY HIGHLY IMPERCEPTIBLE ADVERSARIAL DISTURBANCES

Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclas-sification.

Data and Resources

Cite this as

Ali Shahin Shamsabadi, Francisco Sepúlveda Teixeira, Alberto Abad, Bhiksha Raj, Andrea Cavallaro, Isabel Trancoso (2024). Dataset: FOOLHD: FOOLING SPEAKER IDENTIFICATION BY HIGHLY IMPERCEPTIBLE ADVERSARIAL DISTURBANCES. https://doi.org/10.57702/648me1q0

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2011.08483
Author Ali Shahin Shamsabadi
More Authors
Francisco Sepúlveda Teixeira
Alberto Abad
Bhiksha Raj
Andrea Cavallaro
Isabel Trancoso
Homepage https://fsepteixeira.github.io/FoolHD/