M-to-N Backdoor Paradigm: A Stealthy and Fuzzy Attack to Deep Learning Models.
Linshan HouZhongyun HuaYuhong LiLeo Yu ZhangPublished in: CoRR (2022)
Keyphrases
- learning models
- machine learning
- loss function
- learning algorithm
- semi supervised learning
- learning tasks
- conditional random fields
- machine learning algorithms
- learning paradigms
- fuzzy logic
- machine learning models
- classification models
- learning problems
- neural network
- active learning
- pairwise
- support vector
- genetic algorithm
- data sets
- intermediate concepts