scholarly journals Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation

2021 ◽  
Author(s):  
Haoyan Xu ◽  
Ziheng Duan ◽  
Yueyang Wang ◽  
Jie Feng ◽  
Runjian Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Graph Partitioning ◽  
Graph Matching ◽  
Graph Similarity ◽  
Hierarchical Graph ◽  
Similarity Computation

scholarly journals Graph-partitioning based convolutional neural network for earthquake detection using a seismic array

2020 ◽  
Author(s):  
Keisuke Yano ◽  
Takahiro Shiina ◽  
Sumito Kurata ◽  
Aitaro Kato ◽  
Fumiyasu Komaki ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Graph Partitioning ◽  
Seismic Array ◽  
Earthquake Detection

Hierarchical graph partitioning

2014 ◽  
Author(s):  
Mohammadtaghi Hajiaghayi ◽  
Theodore Johnson ◽  
Mohammad Reza Khani ◽  
Barna Saha
Keyword(s):  
Graph Partitioning ◽  
Hierarchical Graph

Efficient hierarchical graph partitioning for image segmentation by optimum oriented cuts

2020 ◽  
Vol 131 ◽  
pp. 185-192 ◽  
Author(s):  
Hans H.C. Bejar ◽  
Silvio Jamil Ferzoli Guimaraes ◽  
Paulo A.V. Miranda
Keyword(s):  
Image Segmentation ◽  
Graph Partitioning ◽  
Hierarchical Graph

scholarly journals Order Matters: Semantic-Aware Neural Networks for Binary Code Similarity Detection

2020 ◽  
Vol 34 (01) ◽  
pp. 1145-1152 ◽  
Author(s):  
Zeping Yu ◽  
Rui Cao ◽  
Qiyi Tang ◽  
Sen Nie ◽  
Junzhou Huang ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Security ◽  
Semantic Information ◽  
Binary Code ◽  
Graph Matching ◽  
Control Flow ◽  
Binary Function ◽  
Similarity Detection ◽  
Block Level

Binary code similarity detection, whose goal is to detect similar binary functions without having access to the source code, is an essential task in computer security. Traditional methods usually use graph matching algorithms, which are slow and inaccurate. Recently, neural network-based approaches have made great achievements. A binary function is first represented as an control-flow graph (CFG) with manually selected block features, and then graph neural network (GNN) is adopted to compute the graph embedding. While these methods are effective and efficient, they could not capture enough semantic information of the binary code. In this paper we propose semantic-aware neural networks to extract the semantic information of the binary code. Specially, we use BERT to pre-train the binary code on one token-level task, one block-level task, and two graph-level tasks. Moreover, we find that the order of the CFG's nodes is important for graph similarity detection, so we adopt convolutional neural network (CNN) on adjacency matrices to extract the order information. We conduct experiments on two tasks with four datasets. The results demonstrate that our method outperforms the state-of-art models.

Sign in / Sign up

Export Citation Format

Share Document