Black-Box Adversarial Attacks on Graph Neural Networks with Limited Node Access.
Jiaqi MaShuangrui DingQiaozhu MeiPublished in: CoRR (2020)
Keyphrases
- black box
- neural network
- rule extraction
- graph structure
- directed graph
- hybrid systems
- black boxes
- white box
- random walk
- undirected graph
- white box testing
- nodes of a graph
- finding the shortest path
- artificial neural networks
- integration testing
- path length
- test cases
- weighted graph
- black hole
- case study
- tree structure
- data model
- overlapping communities
- root node
- bipartite graph
- fuzzy logic
- malicious nodes
- small world
- object oriented
- activation function
- access control
- back propagation