讀書筆記17：Adversarial Attacks on Neural Networks for Graph Data
https://arxiv.org/pdf/1805.07984.pdf 看過之後有一個思考，adversarial attack的目標是事先選定一個class，然後選擇攻擊方式，儘可能使得模型把樣本分類成這個類別，並且class probability和原class的probability拉開差距，但是可不可以將目標設定爲最小化原分類class的probability，也就是隻將目標定位爲使ta
相關文章
- 1. Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering讀書筆記
- 2. cousera「Neural NetWorks and Deep learning"讀書筆記
- 3. Paper Notes: A Comprehensive Survey on Graph Neural Networks
- 4. 【生成對抗樣本】Simple Black-Box Adversarial Attacks on Deep Neural Networks
- 5. Graph Neural Networks for Social Recommendation
- 6. 論文閱讀筆記A Comprehensive Survey on Graph Neural Networks
- 7. Graph Convolutional Networks for Text Classification閱讀筆記
- 8. Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
- 9. AutoGAN: Neural Architecture Search for Generative Adversarial Networks閱讀筆記
- 10. 筆記《Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels》-NeurIPS 2019
- 更多相關文章...
- • Eclipse 添加書籤 - Eclipse 教程
- • ASP.NET Razor - 標記 - ASP.NET 教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • JDK13 GA發佈：5大特性解讀
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering讀書筆記
- 2. cousera「Neural NetWorks and Deep learning"讀書筆記
- 3. Paper Notes: A Comprehensive Survey on Graph Neural Networks
- 4. 【生成對抗樣本】Simple Black-Box Adversarial Attacks on Deep Neural Networks
- 5. Graph Neural Networks for Social Recommendation
- 6. 論文閱讀筆記A Comprehensive Survey on Graph Neural Networks
- 7. Graph Convolutional Networks for Text Classification閱讀筆記
- 8. Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
- 9. AutoGAN: Neural Architecture Search for Generative Adversarial Networks閱讀筆記
- 10. 筆記《Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels》-NeurIPS 2019