An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection
Anomaly detection is one of the many challenging areas in cybersecurity. The anomaly can occur in many forms, such as fraudulent credit card transactions, network intrusions, and anomalous imageries or documents. One of the most common challenges in anomaly detection is the obscurity of the normal s...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2023.9020035 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832543051023646720 |
|---|---|
| author | Faleh Alshameri Ran Xia |
| author_facet | Faleh Alshameri Ran Xia |
| author_sort | Faleh Alshameri |
| collection | DOAJ |
| description | Anomaly detection is one of the many challenging areas in cybersecurity. The anomaly can occur in many forms, such as fraudulent credit card transactions, network intrusions, and anomalous imageries or documents. One of the most common challenges in anomaly detection is the obscurity of the normal state and the lack of anomalous samples. Traditionally, this problem is tackled by using resampling techniques or choosing models that approximate the distribution of the normal states. Variational AutoEncoder (VAE) has been studied in anomaly detections despite being more suitable in generative tasks. This study aims to explore the usage of VAE in credit card anomaly detection and evaluate latent space sampling techniques. In this study, we evaluate the usage of the convolutional network-based VAE model on a credit card transaction dataset. We train two VAE models, one with a large number of normal data and one with a small number of anomalous data. We compare the performance of both VAE models and evaluate the latent space of both VAE models by rescaling them with reconstruction error vectors. We also compare the effectiveness of the VAE model with other anomaly detection models when they are trained on imbalanced dataset. |
| format | Article |
| id | doaj-art-e5bbb3ec49a04a9bad70a5633d6c835a |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-e5bbb3ec49a04a9bad70a5633d6c835a2025-02-03T11:53:24ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-09-017371872910.26599/BDMA.2023.9020035An Evaluation of Variational Autoencoder in Credit Card Anomaly DetectionFaleh Alshameri0Ran Xia1School of Business, University of Maryland Global Campus, Adelphi, MD 20783, USASchool of Technology and Innovation, College of Business, Innovation, Leadership and Technology, Marymount University, Arlington, VA 22207, USAAnomaly detection is one of the many challenging areas in cybersecurity. The anomaly can occur in many forms, such as fraudulent credit card transactions, network intrusions, and anomalous imageries or documents. One of the most common challenges in anomaly detection is the obscurity of the normal state and the lack of anomalous samples. Traditionally, this problem is tackled by using resampling techniques or choosing models that approximate the distribution of the normal states. Variational AutoEncoder (VAE) has been studied in anomaly detections despite being more suitable in generative tasks. This study aims to explore the usage of VAE in credit card anomaly detection and evaluate latent space sampling techniques. In this study, we evaluate the usage of the convolutional network-based VAE model on a credit card transaction dataset. We train two VAE models, one with a large number of normal data and one with a small number of anomalous data. We compare the performance of both VAE models and evaluate the latent space of both VAE models by rescaling them with reconstruction error vectors. We also compare the effectiveness of the VAE model with other anomaly detection models when they are trained on imbalanced dataset.https://www.sciopen.com/article/10.26599/BDMA.2023.9020035anomaly detectionoptimizationimbalanced datasetgenerative modelingconvolutional neural network (cnn)variational autoencoder (vae)latent space scalingreconstruction error |
| spellingShingle | Faleh Alshameri Ran Xia An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection Big Data Mining and Analytics anomaly detection optimization imbalanced dataset generative modeling convolutional neural network (cnn) variational autoencoder (vae) latent space scaling reconstruction error |
| title | An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection |
| title_full | An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection |
| title_fullStr | An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection |
| title_full_unstemmed | An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection |
| title_short | An Evaluation of Variational Autoencoder in Credit Card Anomaly Detection |
| title_sort | evaluation of variational autoencoder in credit card anomaly detection |
| topic | anomaly detection optimization imbalanced dataset generative modeling convolutional neural network (cnn) variational autoencoder (vae) latent space scaling reconstruction error |
| url | https://www.sciopen.com/article/10.26599/BDMA.2023.9020035 |
| work_keys_str_mv | AT falehalshameri anevaluationofvariationalautoencoderincreditcardanomalydetection AT ranxia anevaluationofvariationalautoencoderincreditcardanomalydetection AT falehalshameri evaluationofvariationalautoencoderincreditcardanomalydetection AT ranxia evaluationofvariationalautoencoderincreditcardanomalydetection |