TgrApp: Anomaly Detection and Visualization of Large-Scale Call Graphs

Authors

  • Mirela T. Cazzolato Carnegie Mellon University (CMU) University of São Paulo (ICMC-USP)
  • Saranya Vijayakumar Carnegie Mellon University (CMU)
  • Xinyi Zheng Carnegie Mellon University (CMU)
  • Namyong Park Carnegie Mellon University (CMU)
  • Meng-Chieh Lee Carnegie Mellon University (CMU)
  • Duen Horng Chau Georgia Institute of Technology
  • Pedro Fidalgo Mobileum University Institute of Lisbon (ISCTE-IUL)
  • Bruno Lages Mobileum
  • Agma J. M. Traina University of São Paulo (ICMC-USP)
  • Christos Faloutsos Carnegie Mellon University (CMU)

DOI:

https://doi.org/10.1609/aaai.v37i13.27062

Keywords:

Anomaly Detection, Graph Mining, Phone Call Network

Abstract

Given a million-scale dataset of who-calls-whom data containing imperfect labels, how can we detect existing and new fraud patterns? We propose TgrApp, which extracts carefully designed features and provides visualizations to assist analysts in spotting fraudsters and suspicious behavior. Our TgrApp method has the following properties: (a) Scalable, as it is linear on the input size; and (b) Effective, as it allows natural interaction with human analysts, and is applicable in both supervised and unsupervised settings.
AAAI-23 Proceedings Cover

Downloads

Published

2023-09-06

How to Cite

Cazzolato, M. T., Vijayakumar, S., Zheng, X., Park, N., Lee, M.-C., Chau, D. H., Fidalgo, P., Lages, B., Traina, A. J. M., & Faloutsos, C. (2023). TgrApp: Anomaly Detection and Visualization of Large-Scale Call Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16410-16412. https://doi.org/10.1609/aaai.v37i13.27062

Issue

Vol. 37 No. 13: AAAI-23 Special Programs, IAAI-23, EAAI-23, Student Papers and Demonstrations

Section

Demonstrations