Francisco Sepúlveda Teixeira

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 misclassification. In this work, we propose a white-box steganography-inspired adversarial attack that generates imperceptible adversarial perturbations against a speaker i…