Interpretable Adversarial Example Detection Via High-Level Concept Activation Vector

COMPUTERS & SECURITY（2025）

引用 0|浏览6

关键词

Deep learning,Adversarial machine learning,Model explainability,Adversarial defense,Concept activation vector

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要