研究论文开放获取
Robust knowledge distillation based on feature variance against backdoored teacher model
Jinyin Chen, Xiaoming Zhao, Haibin Zheng, Xiao Li, Sheng Xiang, Haifeng Guo
Zhejiang University of Technology
来源Applied Soft Computing
年份2024
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
摘要 · 节选
暂未获取摘要。可打开原文或 PDF,后续可基于全文生成更完整的速读。
逐年被引趋势
530
24
25
526
关键指标
10
被引次数 · OpenAlex
1.04
领域内被引倍数
同类平均 = 1
同类平均 = 1
前 24%
引用位次
同领域 · 同年份 · 同类型
同领域 · 同年份 · 同类型
64
参考文献
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:文献信息
论文问答
当前基于文献信息回答
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIAdversarial Robustness in Machine Learning
Advanced Neural Network Applications · Domain Adaptation and Few-Shot Learning
参考文献 64
Distilling the Knowledge in a Neural Network
被引 26,325Geoffrey E. Hinton, Oriol Vinyals, Dean, Jeff · arXiv (Cornell University) · 2015
Graph mining: Laws, generators, and algorithms
被引 623Deepayan Chakrabarti, Christos Faloutsos · ACM Computing Surveys · 2006
The German Traffic Sign Recognition Benchmark: A multi-class classification competition
被引 1,255Johannes Stallkamp, Marc Schlipsing, Jan Salmen · International Joint Conference on Neural Networks (IJCNN) · 2011
此处列出前 3 条
引用本文 10
Energy-efficient deep learning-based intrusion detection system for edge computing: a novel DNN-KDQ model
被引 76Hafiz Gulfam Ahmad Umar, Iqra Yasmeen, Muhammad Aoun · Journal of Cloud Computing Advances Systems and Applications · 2025
Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
被引 22Shuai Zhao, Leilei Gan, Zhongliang Guo · arXiv (Cornell University) · 2024
On-device large language models: a survey of model compression and system optimization
被引 9Wanyi Chen, Junhao Wang, Yiwei Zhang · Artificial Intelligence Review · 2026
按被引量排序,此处列出前 3 条