Open Access

ARTICLE

CDR2IMG: A Bridge from Text to Image in Telecommunication Fraud Detection

by Zhen Zhen¹, Jian Gao^1,2,*

1 School of Information Network Security, People’s Public Security University of China, Beijing, 100038, China
2 Key Laboratory of Safety Precautions and Risk Assessment, Ministry of Public Security, Beijing, 102623, China

* Corresponding Author: Jian Gao. Email:

Computer Systems Science and Engineering 2023, 47(1), 955-973. https://doi.org/10.32604/csse.2023.039525

Received 02 February 2023; Accepted 11 April 2023; Issue published 26 May 2023

Abstract

Telecommunication fraud has run rampant recently worldwide. However, previous studies depend highly on expert knowledge-based feature engineering to extract behavior information, which cannot adapt to the fast-changing modes of fraudulent subscribers. Therefore, we propose a new taxonomy that needs no hand-designed features but directly takes raw Call Detail Records (CDR) data as input for the classifier. Concretely, we proposed a fraud detection method using a convolutional neural network (CNN) by taking CDR data as images and applying computer vision techniques like image augmentation. Comprehensive experiments on the real-world dataset from the 2020 Digital Sichuan Innovation Competition show that our proposed method outperforms the classic methods in many metrics with excellent stability in both the changes of quantity and the balance of samples. Compared with the state-of-the-art method, the proposed method has achieved about 89.98% F1-score and 92.93% AUC, improving 2.97% and 0.48%, respectively. With the augmentation technique, the model’s performance can be further enhanced by a 91.09% F1-score and a 94.49% AUC respectively. Beyond telecommunication fraud detection, our method can also be extended to other text datasets to automatically discover new features in the view of computer vision and its powerful methods.

---

Keywords

---