Adversarial Attacks in Underwater Acoustic Target Recognition with Deep Learning Models

Deep learning models can produce unstable results by introducing imperceptible perturbations that are difficult for humans to recognize. This can have a significant impact on the accuracy and security of deep learning applications due to their poorly understood interpretability. As a field critical...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Sheng Feng, Xiaoqian Zhu, Shuqing Ma, Qiang Lan
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2023-11-01
coleção:	Remote Sensing
Assuntos:	model security imperceptible perturbations model interpretability Mel-spectrogram
Acesso em linha:	https://www.mdpi.com/2072-4292/15/22/5386
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!