Learning from Limited Heterogeneous Training Data: Meta-Learning for Unsupervised Zero-Day Web Attack Detection across Web Domains.
Peiyang LiYe WangQi LiZhuotao LiuKe XuJu RenZhiying LiuRuilin LinPublished in: CoRR (2023)
Keyphrases
- meta learning
- supervised learning
- learning algorithm
- learning tasks
- training data
- inductive learning
- learning process
- model selection
- unsupervised learning
- reinforcement learning
- prior knowledge
- data sets
- real world
- user generated content
- transfer learning
- machine learning algorithms
- knowledge acquisition
- semi supervised
- classification accuracy