Cybercrime Prediction via Geographically Weighted Learning: The Case Study of GCC

Document Type

Conference Proceeding

Source of Publication

2024 International Jordanian Cybersecurity Conference (IJCC)

Publication Date

12-18-2024

Abstract

Cybercrime is becoming more sophisticated, thus raising significant challenges for both private and government sectors. Inspired by the success of Geographically Weighted Regression and its accounting for spatial variations, we propose GeogGNN - A graph neural network model that accounts for geographical latitude and longitudinal points to combat cybercrimes. Using a synthetically generated dataset, we apply the algorithm for a 4-class classification problem in cybersecurity with seemingly realistic geographic coordinates centered in the Gulf Cooperation Council (GCC) region as a case study. Results show that GeogGNN has higher accuracy than standard neural networks and convolutional neural networks, which treat the coordinates as features. Therefore, the GeogGNN model is a powerful tool for handling complex, geographically distributed data as it effectively captures the underlying structure and dependencies between data points involving complex relationships.

ISBN

979-8-3315-1846-2

Publisher

IEEE

Volume

00

First Page

55

Last Page

61

Disciplines

Computer Sciences

Keywords

Cybercrime, Geographically Weighted Learning, Graph Neural Network, Cybersecurity, GCC

Indexed in Scopus

no

Open Access

no

Link to Full Text

Share

COinS