主题为”基于GAN的恶意软件对抗样本生成“。首先介绍了恶意软件发展现状，引出基于模式匹配、特征空间和问题空间三种方式去检测恶意软件。然后介绍了如何生成对抗样本攻击恶意软件检测器，详细介绍了基于GAN的恶意软件对抗样本的MalGAN框架，并对实验结果进行了对比。最后总结了结构性对抗样本的约束：可用转换 、保留语义、似然性、副作用特征。
-
Updated
Jul 25, 2021 - Python
#
malgan
Here are 2 public repositories matching this topic...
Stacked ensemble malware detection with adversarial (MalGAN-inspired) robustness evaluation using EMBER dataset.
machine-learning deep-learning cybersecurity gan ensemble-learning research-project malware-detection adversarial-machine-learning malgan
-
Updated
Feb 15, 2026
Improve this page
Add a description, image, and links to the malgan topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the malgan topic, visit your repo's landing page and select "manage topics."