相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Review
Computer Science, Information Systems
Asma Cherif et al.
Summary: Credit card fraud is a serious problem due to emerging technologies like contactless payment. This article provides an in-depth review of cutting-edge research from 2015 to 2021 on detecting and predicting fraudulent credit card transactions. The study reveals limited investigation into deep learning, highlighting the need for more research to address challenges in detecting fraud using new technologies. This study serves as a valuable resource for academic and industrial researchers in evaluating fraud detection systems and designing solutions.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Bin Shi et al.
Summary: This paper proposes a novel graph neural network model, Eagle, for detecting tax evasion in a heterogeneous graph. With the guidance of designed metapaths and a hierarchical attention mechanism, Eagle can extract comprehensive features from taxpayers' features and relations, improving the performance of tax evasion detection.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Ziwei Zhang et al.
Summary: This survey comprehensively reviews the application of deep learning methods on graph data. The existing methods are categorized into five types, and their development history, differences, and compositions are covered in a systematic manner. Potential future research directions are also discussed.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Shunxin Xiao et al.
Summary: This paper provides a comprehensive review of applying graph neural networks to the node classification task. The state-of-the-art methods are discussed and extensive comparative experiments are conducted. Suggestions for future research are also provided.
MACHINE VISION AND APPLICATIONS
(2022)
Article
Computer Science, Theory & Methods
Lin Liu et al.
Summary: Anomaly detection for smart contracts is important in preventing security risks like financial fraud, and the key is to extract features from complex smart contracts and effectively identify abnormal contracts. This study introduces a Heterogeneous Graph Transformer Networks (S_HGTNs) suitable for smart contract anomaly detection on the Ethereum platform.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Review
Computer Science, Artificial Intelligence
Waleed Hilal et al.
Summary: With technology advancements and economic growth, financial fraud has become more common, leading to significant losses for institutions and consumers. Traditional fraud prevention systems are not sufficient, highlighting the importance of fraud detection systems. Researchers have focused on anomaly detection techniques using statistical, artificial intelligence, and machine learning models. Recently, there has been interest in semi-supervised and unsupervised learning models.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Rafael Van Belle et al.
Summary: This paper evaluates the predictive performance of state-of-the-art inductive graph representation learning algorithms on credit card transaction fraud networks and demonstrates the benefits of graph-level undersampling for representation learning in imbalanced networks.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Dawei Cheng et al.
Summary: This article introduces a spatial-temporal attention-based graph network (STAGN) for credit card fraud detection, and demonstrates its superiority in fraud detection and knowledge discovery through experiments and research with domain experts.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Information Systems
Bingxue Fu et al.
Summary: With the use of graph convolutional networks, a high-performance model for detecting phishing fraud in blockchain cryptocurrency networks has been developed. The model divides the transaction graph into sender and receiver graphs, transfers the edge features, and uses a double-layer graph convolution network for feature learning. The model achieved better performance than other models, with an accuracy of 88.02% and an F1 score of 88.14% on test data.
INTERNATIONAL JOURNAL OF INFORMATION SECURITY
(2022)
Article
Automation & Control Systems
A. I. Sergadeeva et al.
Summary: This study proposes a method for detecting bank fraud based on graph neural networks. Financial transactions are represented in the form of a graph and analyzed with a graph neural network with the goal of detecting transactions typical of fraud schemes. The results of experimental tests indicate the high potential of the proposed approach.
AUTOMATIC CONTROL AND COMPUTER SCIENCES
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Xincheng Duan et al.
Summary: This paper presents a method for identifying phishing accounts in the Ethereum system using a graph classification network model. By combining node embedding algorithm and graph convolutional neural networks, the method achieves high detection precision.
WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS (WASA 2022), PT I
(2022)
Proceedings Paper
Computer Science, Cybernetics
Sijia Li et al.
Summary: This paper proposes a method called TTAGN to enhance phishing scams detection performance on Ethereum by constructing edge and node representations of the transaction network. The effectiveness of this method is demonstrated through evaluations on real-world datasets.
PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22)
(2022)
Article
Computer Science, Theory & Methods
Jiajun Zhou et al.
Summary: This paper presents a method for Ethereum account identification and proposes an end-to-end graph neural network framework called Ethident, which reveals and de-anonymizes account behavior, providing support for financial security and market regulation. Comprehensive experiments on Ethereum datasets demonstrate the superior performance of this framework.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Information Systems
Zi Ye et al.
Summary: This paper provides a comprehensive overview of GNN-based technologies for different KG tasks, as well as the related AI applications based on advanced GNN methods. It offers new insights for further study of KG and GNN.
Article
Multidisciplinary Sciences
Pingfan Xia et al.
Summary: Money laundering is a criminal act that seeks to conceal the illegal gains of criminals, leading to significant harm to a country's economy, political order, and social stability. To predict money laundering risks effectively, a hybrid spatiotemporal prediction model MGC-LSTM is proposed, utilizing LSTM and GCN to learn the dependency between different money laundering transactions, achieving better performance compared to other state-of-the-art algorithms.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Hwan Kim et al.
Summary: Graph neural networks (GNNs) have been extensively researched in recent years and have been successful in tasks such as node classification, link prediction, and graph classification, due to their highly expressive capability via message passing. Detecting anomalies in a graph is crucial in analyzing complex systems, and GNN-based methods leverage graph attributes and structures to appropriately score anomalies.
Article
Computer Science, Artificial Intelligence
Zonghan Wu et al.
Summary: This article provides a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. It discusses the taxonomy of GNNs, their applications, and summarizes open-source codes, benchmark data sets, and model evaluation. The article also proposes potential research directions in this rapidly growing field.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Aditya Singh et al.
Summary: The rise of cryptocurrency has presented both opportunities and challenges, with a growing demand for transparent networks resilient to illegal activities. Existing technologies still struggle with performance in future time steps.
20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2021)
(2021)
Review
Multidisciplinary Sciences
Xiaoqian Zhu et al.
Summary: This paper provides a comprehensive overview of intelligent financial fraud detection practices, analyzing the new features of fraud risk caused by the pandemic and reviewing the development of data types used in fraud detection practices. It summarizes the evolution of methods in financial fraud detection and discusses the emerging Graph Neural Network methods in the post-pandemic era. Some key challenges and potential directions are proposed to inspire future intelligent financial fraud detection efforts.
Article
Computer Science, Artificial Intelligence
HongYun Cai et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2018)
Article
Computer Science, Theory & Methods
Mohiuddin Ahmed et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2016)
Review
Computer Science, Hardware & Architecture
Aisha Abdallah et al.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2016)
Article
Computer Science, Artificial Intelligence
Leman Akoglu et al.
DATA MINING AND KNOWLEDGE DISCOVERY
(2015)
