发简信
IP属地：广东
-
Adversarial Distributional Training
Adversarial Distributional Training for Robust Deep LearningZhijie Deng,...
-
定制化对抗训练Customized Adversarial TrainingCAT: Customized Adversarial Training for Improved RobustnessMinhao Cheng...
-
聚类训练Clustering Training for Robustness
ClustTR: Clustering Training for RobustnessMotasem Alfarra, Juan C. Pére...
-
对抗样本领域综述文章推荐
对于刚接触对抗样本领域的小伙伴们来说，看到领域内众多文章时，简直眼花缭乱。这时候，如果一篇好的综述概括了当前领域内的主要进展，提供给我们该领域的...
-
[论文笔记]DeepFool: a simple and accurate method to fool deep neural networks题目：DeepFool: a simple and accurate method to fool deep neural networks地址...
-
[论文笔记]Towards Evaluating the Robustness of Neural Networks
题目：Towards Evaluating the Robustness of Neural Networks地址：https://arxiv....
-
[论文阅读笔记]One pixel attack for fooling deep neural networks
论文题目：One pixel attack for fooling deep neural networks论文地址：https://arxiv...
-
对抗攻击方法汇总（持续更新）
自从2014年Szegedy等人提出对抗样本以来，不断有研究者提出新的对抗攻击方法。本文汇总了当前已有的绝大多数算法，以抛砖引玉用，并不断更新。...
-
[论文阅读笔记]The Limitations of Deep Learning in Adversarial Settings论文题目：The Limitations of Deep Learning in Adversarial Settings论文地址：https:...