Black-Box Adversarial Attack on Graph Neural Networks Based on Node Domain Knowledge.
Qin SunZheng YangZhiming LiuQuan ZouPublished in: KSEM (1) (2023)
Keyphrases
- black box
- domain knowledge
- neural network
- rule extraction
- graph structure
- directed graph
- hybrid systems
- black boxes
- white box
- edge weights
- finding the shortest path
- artificial neural networks
- weighted graph
- nodes of a graph
- root node
- tree structure
- random walk
- test cases
- overlapping communities
- undirected graph
- back propagation
- attack graph
- prior knowledge
- path length
- state transition
- integration testing
- open source
- fuzzy logic
- case study
- shortest path
- error rate
- learning algorithm
- betweenness centrality
- machine learning
- data sets
- database