A Hard Label Black-box Adversarial Attack Against Graph Neural Networks.
Jiaming MuBinghui WangQi LiKun SunMingwei XuZhuotao LiuPublished in: CCS (2021)
Keyphrases
- black box
- neural network
- rule extraction
- hybrid systems
- black boxes
- white box
- attack graph
- label noise
- label propagation
- graph theory
- pattern recognition
- artificial neural networks
- weighted graph
- white box testing
- integration testing
- back propagation
- random walk
- test cases
- active learning
- multi agent
- multilayer perceptron
- state transition
- development process