Dataset Groups Activity Stream 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. BibTex: @dataset{Ali_Shahin_Shamsabadi_and_Francisco_Sepúlveda_Teixeira_and_Alberto_Abad_and_Bhiksha_Raj_and_Andrea_Cavallaro_and_Isabel_Trancoso_2024, abstract = {Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclas-sification.}, author = {Ali Shahin Shamsabadi and Francisco Sepúlveda Teixeira and Alberto Abad and Bhiksha Raj and Andrea Cavallaro and Isabel Trancoso}, doi = {10.57702/648me1q0}, institution = {No Organization}, keyword = {'adversarial attacks', 'audio files', 'deep learning', 'speaker identification'}, month = {dec}, publisher = {TIB}, title = {FOOLHD: FOOLING SPEAKER IDENTIFICATION BY HIGHLY IMPERCEPTIBLE ADVERSARIAL DISTURBANCES}, url = {https://service.tib.eu/ldmservice/dataset/foolhd--fooling-speaker-identification-by-highly-imperceptible-adversarial-disturbances}, year = {2024} }
