Redeem Myself: Purifying Backdoors in Deep Learning Models using Self Attention Distillation.
Xueluan GongYanjiao ChenWang YangQian WangYuzhe GuHuayang HuangChao ShenPublished in: SP (2023)
Keyphrases
- learning models
- machine learning
- loss function
- learning tasks
- learning algorithm
- semi supervised learning
- machine learning algorithms
- classification models
- conditional random fields
- learning problems
- authoring tool
- machine learning models
- learning paradigms
- intermediate concepts
- artificial neural networks
- data sets
- feature selection
- natural language processing
- information retrieval