跳至主導覽
跳至搜尋
跳過主要內容
國立陽明交通大學研發優勢分析平台 首頁
English
中文
首頁
人員
單位
研究成果
計畫
獎項
活動
貴重儀器
影響
按專業知識、姓名或所屬機構搜尋
A Black-Box Adversarial Attack via Deep Reinforcement Learning on the Feature Space
Lyue Li, Amir Rezapour,
Wen Guey Tzeng
資訊科學與工程研究所
研究成果
:
Conference contribution
›
同行評審
總覽
指紋
指紋
深入研究「A Black-Box Adversarial Attack via Deep Reinforcement Learning on the Feature Space」主題。共同形成了獨特的指紋。
排序方式
重量
按字母排序
Keyphrases
Feature Space
100%
Original Image
100%
Transfer Rate
100%
Deep Reinforcement Learning (deep RL)
100%
Adversarial Images
100%
Black-box Adversarial Attack
100%
Attack Success Rate
100%
Attacker
50%
Reinforcement Learning
50%
Transferability
50%
Denoising Techniques
50%
Norm Distance
50%
Defense Mechanisms
50%
Learning to Learn
50%
Computer Science
Feature Space
100%
Deep Reinforcement Learning
100%
Adversarial Machine Learning
100%
de-noising
50%
Attackers
50%
Reinforcement Learning
50%
Imperceptibility
50%