Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning.
Antonio Emanuele CinàKathrin GrosseAmbra DemontisSebastiano VasconWerner ZellingerBernhard Alois MoserAlina OpreaBattista BiggioMarcello PelilloFabio RoliPublished in: ACM Comput. Surv. (2023)
Keyphrases
- training data
- machine learning
- learning algorithm
- decision trees
- supervised learning
- training patterns
- training process
- pattern recognition
- machine learning algorithms
- intrusion detection
- semi supervised learning
- pattern mining
- data sets
- knowledge representation
- prior knowledge
- learning tasks
- natural language processing
- feature selection
- training examples
- statistical methods
- information security
- network security
- statistical databases
- machine learning methods
- security issues
- access control
- test set
- support vector machine
- active learning
- training set
- computer vision
- artificial intelligence
- neural network
- test data
- unlabeled data
- labeled data
- data analysis
- classification models
- information systems