【譯】Attacks against machine learning — an overview
這篇博客文章調查了針對AI（人工智能）系統的攻擊技術以及如何防範它們。html 在較高級別，對分類器的攻擊能夠分爲三種類型：node 對抗性輸入 ，這是特製的輸入，其目的是可靠地錯誤分類以逃避檢測。 對抗性輸入包括旨在逃避防病毒的惡意文檔，以及試圖逃避垃圾郵件過濾器的電子郵件。 數據中毒攻擊 ，涉及將訓練對抗數據提供給分類器。 咱們觀察到的最多見的攻擊類型是模型傾斜，攻擊者試圖以這樣的方式污染訓練
相關文章
- 1. Practical Black-Box Attacks against Machine Learning
- 2. [paper]Practical Black-Box Attacks against Machine Learning
- 3. Practical Black-Box Attacks against Machine Learning 閱讀筆記
- 4. 論文筆記：Membership Inference Attacks Against Machine Learning Models
- 5. 論文解析：Membership Inference Attacks Against Machine Learning Models（一看即懂）
- 6. Learning Machine Learning, Part 1: An Introduction
- 7. An example machine learning notebook
- 8. ÆGIS: Shielding Vulnerable Smart Contracts Against Attacks
- 9. An Introduction to Machine Learning with Python
- 10. Supervised Speech Separation Based on Deep Learning-An Overview
- 更多相關文章...
- • Docker Machine - Docker教程
- • Eclipse 編譯項目 - Eclipse 教程
- • Java Agent入門實戰（一）-Instrumentation介紹與使用
- • Java Agent入門實戰（三）-JVM Attach原理與使用
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. Practical Black-Box Attacks against Machine Learning
- 2. [paper]Practical Black-Box Attacks against Machine Learning
- 3. Practical Black-Box Attacks against Machine Learning 閱讀筆記
- 4. 論文筆記：Membership Inference Attacks Against Machine Learning Models
- 5. 論文解析：Membership Inference Attacks Against Machine Learning Models（一看即懂）
- 6. Learning Machine Learning, Part 1: An Introduction
- 7. An example machine learning notebook
- 8. ÆGIS: Shielding Vulnerable Smart Contracts Against Attacks
- 9. An Introduction to Machine Learning with Python
- 10. Supervised Speech Separation Based on Deep Learning-An Overview