Smart Contract Vulnerability Detection: From Pure Neural Network to Interpretable Graph Feature and Expert Pattern Fusion.
Zhenguang LiuPeng QianXiang WangLei ZhuQinming HeShouling JiPublished in: IJCAI (2021)
Keyphrases
- neural network
- pattern detection
- artificial neural networks
- pattern matching
- false alarms
- detection method
- multi modal fusion
- multiple features
- data fusion
- genetic algorithm
- automatic detection
- pattern recognition
- supply chain
- feature vectors
- detection algorithm
- associative memory
- information fusion
- feature level
- directed graph
- connected components
- false positives
- object detection
- structured data
- decision level fusion
- neural network is trained
- graph matching
- graph theory
- graph model
- graph databases
- vector representation
- graph representation
- preprocessing stage
- feature fusion
- image features
- feature maps
- knn
- directed acyclic graph
- fuzzy logic
- detection rate
- human experts
- back propagation