A Black-Box Adversarial Attack via Deep Reinforcement Learning on the Feature Space.
Lyue LiAmir RezapourWen-Guey TzengPublished in: DSC (2021)
Keyphrases
- black box
- feature space
- reinforcement learning
- multi agent
- black boxes
- white box
- function approximation
- test cases
- integration testing
- high dimensional
- state space
- input space
- feature extraction
- data points
- feature vectors
- kernel function
- hybrid systems
- rule extraction
- reinforcement learning algorithms
- model free
- feature selection
- markov decision processes
- machine learning
- mean shift
- optimal policy
- training samples
- principal component analysis
- image retrieval
- learning algorithm
- kernel methods
- temporal difference
- white box testing
- state transition
- dimensionality reduction
- learning capabilities
- relational databases
- database