A Hard Label Black-box Adversarial Attack Against Graph Neural Networks.
Jiaming MuBinghui WangQi LiKun SunMingwei XuZhuotao LiuPublished in: CoRR (2021)
Keyphrases
- black box
- neural network
- rule extraction
- hybrid systems
- black boxes
- white box
- label propagation
- graph theory
- attack graph
- pattern recognition
- test cases
- weighted graph
- state transition
- artificial neural networks
- white box testing
- graph structure
- directed graph
- databases
- random walk
- fuzzy logic
- integration testing
- label noise
- multilayer perceptron
- computational intelligence
- object oriented