Jan, 2024
GE-AdvGAN:基于梯度编辑的对抗生成模型改进对抗样本的可传递性
GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model
Zhiyu Zhu, Huaming Chen, Xinyi Wang, Jiayu Zhang, Zhibo Jin...
TL;DR通过优化生成器参数的训练过程并引入梯度编辑机制,GE-AdvGAN 算法能够生成高度可迁移的对抗样本并在执行时间上与现有方法相比保持最小化。