ENHANCING TRANSFORMATION-BASED DEFENSES AGAINST ADVERSARIAL ATTACKS WITH A DISTRIBUTION CLASSIFIER
ENHANCING TRANSFORMATION-BASED DEFENSES AGAINST ADVERSARIAL ATTACKS WITH A DISTRIBUTION CLASSIFIER (ICLR 2020) 摘要 we propose a method to improve existing transformation-based defenses. 1 介紹 基於隨機變換的防禦方
相關文章
- 1. MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples
- 2. [paper]Boosting Adversarial Attacks with Momentum
- 3. 對抗樣本(論文解讀四): Adversarial Attacks and Defenses in Images, Graphs and Text: A Review
- 4. Practical Black-Box Attacks against Machine Learning
- 5. Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution
- 6. 論文解讀《Boosting Adversarial Attacks with Momentum》
- 7. TRAINING A CLASSIFIER
- 8. [paper]Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
- 9. Stronger Data Poisoning Attacks Break Data Sanitization Defenses
- 10. ÆGIS: Shielding Vulnerable Smart Contracts Against Attacks
- 更多相關文章...
- • XSLT
- • Docker 安裝 Tomcat - Docker教程
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
- • Java 8 Stream 教程
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. MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples
- 2. [paper]Boosting Adversarial Attacks with Momentum
- 3. 對抗樣本(論文解讀四): Adversarial Attacks and Defenses in Images, Graphs and Text: A Review
- 4. Practical Black-Box Attacks against Machine Learning
- 5. Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution
- 6. 論文解讀《Boosting Adversarial Attacks with Momentum》
- 7. TRAINING A CLASSIFIER
- 8. [paper]Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
- 9. Stronger Data Poisoning Attacks Break Data Sanitization Defenses
- 10. ÆGIS: Shielding Vulnerable Smart Contracts Against Attacks