.png){kind=icon}
返回
Transferable Sparse Adversarial Attack on Modulation Recognition With Generative Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/LCOMM.2024.3373222.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Although Deep neural networks (DNN) can achieve higher performance in automatic modulation recognition, they are known to vulnerable to adversarial perturbations, which are strategically added to inputs can fool the DNN model. In this letter, we propose a novel sparse attack scheme based on adversarial generative networks, which enables more covert attacks while preserving communication quality. This new scheme incorporates adversarial training into the discriminator, which not only improves attack performance but also enhances the stability of the training process for adversarial generative networks. Experimental results demonstrate that the proposed scheme outperforms other sparse attack approaches in terms of generation time and transferability.
Keyword:
Modulation recognition
sparse adversarial attack
deep learning
transferable
generative networks
期刊
IF:
4.4
论文数:
1.3W
被引数:
2.2W
机构
引用论文
.png){kind=icon}
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏
查看更多内容