Toward a Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures

Huming Qiu,Hua Ma,Zhi Zhang,Alsharif Abuadbba,Wei Kang,Anmin Fu,Yansong Gao

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY（2024）

引用 9|浏览33

关键词

Robustness,Threat modeling,Toxicology,Sensitivity,Security,Complexity theory,Adaptation models,Deep learning,robustness,backdoor countermeasure,failure factor

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