【翻譯】Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
文章目錄 文章標題：毒蛙！針對神經網絡的乾淨標籤的中毒攻擊-NeurIPS 2018 摘要 1. 引言 1.1 相關工作 1.2 貢獻 2. 一種簡單的乾淨標籤攻擊 2.1 通過特徵碰撞生成有害數據 2.2 優化過程 3. 遷移學習中的中毒攻擊 3.1 一個一擊必殺的攻擊 4. 對端到端訓練的中毒攻擊 4.1 單毒實例攻擊 4.2 水印：一種增強中毒攻擊威力的方法 4.2.1 多中毒實例攻擊 5.
相關文章
- 1. Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
- 2. Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks 論文閱讀、復現及思考
- 3. 【翻譯】Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
- 4. [S&P 2019翻譯]Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
- 5. Cascade-based attacks on complex networks
- 6. 讀書筆記17：Adversarial Attacks on Neural Networks for Graph Data
- 7. 【生成對抗樣本】Simple Black-Box Adversarial Attacks on Deep Neural Networks
- 8. 論文《On the Number of Linear Regions of Deep Neural Networks》翻譯
- 9. 論文翻譯：A Comprehensive Survey on Graph Neural Networks
- 10. 論文翻譯：2017_Audio super resolution using neural networks
- 更多相關文章...
- • Eclipse 編譯項目 - Eclipse 教程
- • Kotlin 使用命令行編譯 - Kotlin 教程
- • RxJava操作符（一）Creating Observables
- • Docker容器實戰(七) - 容器眼光下的文件系統
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. Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
- 2. Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks 論文閱讀、復現及思考
- 3. 【翻譯】Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
- 4. [S&P 2019翻譯]Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
- 5. Cascade-based attacks on complex networks
- 6. 讀書筆記17：Adversarial Attacks on Neural Networks for Graph Data
- 7. 【生成對抗樣本】Simple Black-Box Adversarial Attacks on Deep Neural Networks
- 8. 論文《On the Number of Linear Regions of Deep Neural Networks》翻譯
- 9. 論文翻譯：A Comprehensive Survey on Graph Neural Networks
- 10. 論文翻譯：2017_Audio super resolution using neural networks