Model-Reuse Attacks on Deep Learning Systems
問題的重要性 機器學習系統是大型、複雜的，開發人員傾向於通過重用一系列通常經過預先訓練的原始模型來構建ML系統，這種「即插即用」的模式加快了ML系統的開發週期，但不利的一面是大多數原始模型都是由第三方提供，它們缺乏標準化或規範化調整，帶來嚴重的安全影響，事實上，在軟件開發中重用外部模塊的風險早就被人們認識，相反，對於採用原始模型作爲ML系統的構建塊的安全性影響，我們知之甚少 場景及假設： 這篇工作
相關文章
- 1. Model-Reuse Attacks on Deep Learning Systems
- 2. A Survey of Recommender Systems Based on Deep Learning （1）
- 3. Paper Reading:Wide & Deep Learning for Recommender Systems
- 4. Wide & Deep Learning for Recommender Systems
- 5. Collaborative Deep Learning for Recommender Systems
- 6. Wide &Deep Learning for Recommender Systems
- 7. [論文解讀]Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- 8. [轉載][paper]Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- 9. PGD:Towards Deep Learning Models Resistant to Adversarial Attacks
- 10. 「Deep Learning」Note on RetinaNet
- 更多相關文章...
- • SVN 安裝 - SVN 教程
- • XQuery 添加元素 和屬性 - XQuery 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. Model-Reuse Attacks on Deep Learning Systems
- 2. A Survey of Recommender Systems Based on Deep Learning （1）
- 3. Paper Reading:Wide & Deep Learning for Recommender Systems
- 4. Wide & Deep Learning for Recommender Systems
- 5. Collaborative Deep Learning for Recommender Systems
- 6. Wide &Deep Learning for Recommender Systems
- 7. [論文解讀]Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- 8. [轉載][paper]Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- 9. PGD:Towards Deep Learning Models Resistant to Adversarial Attacks
- 10. 「Deep Learning」Note on RetinaNet