2019 · 114 citations · 31 references
ComputingComputer ScienceCybercrimeMachine LearningNatural Language ProcessingGraph MiningGraph-based LearningSemantic NetworksSocial Network AnalysisCybercrime Ecosystem AnalysisEmbedding LearningGraph Convolutional NetworksGraph EmbeddingsPlayer IdentityUser AttributionUser EmbeddingsUser Representation Learning
Online underground forums have been widely used by cybercriminals to exchange knowledge and trade in illicit products or services, which have played a central role in the cybercriminal ecosystem. In order to combat the evolving cybercrimes, in this paper, we propose and develop an intelligent system named iDetective to automate the analysis of underground forums for the identification of key players (i.e., users who play the vital role in the value chain). In iDetective, we first introduce an attributed heterogeneous information network (AHIN) for user representation and use a meta-path based approach to incorporate higher-level semantics to build up relatedness over users in underground forums; then we propose Player2Vec to efficiently learn node (i.e., user) representations in AHIN for key player identification. In Player2Vec, we first map the constructed AHIN to a multi-view network which consists of multiple single-view attributed graphs encoding the relatedness over users depicted by different designed meta-paths; then we employ graph convolutional network (GCN) to learn embeddings of each single-view attributed graph; later, an attention mechanism is designed to fuse different embeddings learned based on different single-view attributed graphs for final representations. Comprehensive experiments on the data collections from different underground forums (i.e., Hack Forums, Nulled) are conducted to validate the effectiveness of iDetective in key player identification by comparisons with alternative approaches.
31
Aditya Grover, Jure Leskovec · 2016 · 10.9K citations
The Stanford CoreNLP Natural Language Processing Toolkit
Christopher D. Manning, Mihai Surdeanu, John Bauer et al. · 2014 · 7.2K citations · Full text