GLDOC: detection of implicitly malicious MS-Office documents using graph convolutional networks.
Wenbo WangPeng YiTaotao KouWeitao HanChengyu WangPublished in: Cybersecur. (2024)
Keyphrases
- document collections
- social networks
- average degree
- overlapping communities
- information retrieval
- graph theory
- document retrieval
- xml documents
- detection algorithm
- detect malicious
- fully connected
- graph structures
- network analysis
- information retrieval systems
- random walk
- web documents
- text documents
- metadata
- small world
- edge weights
- biological networks
- vector space model
- weighted graph
- graph structure
- false positives
- network architecture
- document set
- detection method
- online social networks
- document clustering
- structured data
- object detection
- knn