ULAN: A Universal Local Adversarial Network for SAR Target Recognition Based on Layer-Wise Relevance Propagation

Recent studies have proven that synthetic aperture radar (SAR) automatic target recognition (ATR) models based on deep neural networks (DNN) are vulnerable to adversarial examples. However, existing attacks easily fail in the case where adversarial perturbations cannot be fully fed to victim models....

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Meng Du, Daping Bi, Mingyang Du, Xinsong Xu, Zilong Wu
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2022-12-01
Serier:	Remote Sensing
Fag:	deep neural network (DNN) synthetic aperture radar automatic target recognition (SAR-ATR) universal adversarial perturbation (UAP) U-Net attention heatmap layer-wise relevance propagation (LRP)
Online adgang:	https://www.mdpi.com/2072-4292/15/1/21
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!