GSE: Group-wise Sparse and Explainable Adversarial Attacks
收藏DataCite Commons2024-12-16 更新2025-04-16 收录
下载链接：
https://service.tib.eu/ldmservice/dataset/808f30d7-6e48-4bb3-8983-193e53e5cd38
下载链接
链接失效反馈官方服务：
资源简介：
Sparse adversarial attacks fool deep neural networks (DNNs) through minimal pixel perturbations, often regularized by the ℓ0 norm. Recent efforts have replaced this norm with a structural sparsity regularizer, such as the nuclear group norm, to craft group-wise sparse adversarial attacks.
稀疏对抗攻击（Sparse adversarial attacks）通过极小的像素扰动实现对深度神经网络（DNNs）的欺骗，这类攻击通常以ℓ0范数进行正则化。近期的相关研究将该范数替换为结构化稀疏正则器，例如核组范数（nuclear group norm），以构造逐组稀疏的对抗攻击。
提供机构：
TIB
创建时间：
2024-12-16
