Robust knowledge distillation based on feature variance against backdoored teacher model
Authors:
- Jinyin ChenJCJinyin Chen
- Xiaoming ZhaoXZXiaoming Zhao
- Haibin ZhengHZHaibin Zheng
- Xiao LiXLXiao Li
- Sheng XiangSXSheng Xiang
- Haifeng GuoHGHaifeng Guo
- 24 June 2024
- journal article
- research article
- Published by Elsevier in Applied Soft Computing
- Vol. 163
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Natural Science Foundation of Zhejiang Province (LDQ23F020001)
- National Natural Science Foundation of China (62072406)
- National Natural Science Foundation of China (52072343)
This publication has 35 references indexed in Scilit:
- Data augmentation techniques in natural language processingApplied Soft Computing, 2022
- Deep double descent: where bigger models and more data hurt*Journal of Statistical Mechanics: Theory and Experiment, 2021
- Knowledge Distillation: A SurveyInternational Journal of Computer Vision, 2021
- GPT-3: What’s it good for?Natural Language Engineering, 2020
- Special Issue on Evolutionary Computer Vision, Image Processing and Pattern RecognitionApplied Soft Computing, 2020
- BadNets: Evaluating Backdooring Attacks on Deep Neural NetworksIEEE Access, 2019
- Two bi-objective hybrid approaches for the frequent subgraph mining problemApplied Soft Computing, 2018
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices2018
- Self-supervised Knowledge Distillation Using Singular Value Decomposition2018
- A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning2017