Fraud Detection in Payments Transactions: Overview of Existing Approaches and Usage for Instant Payments

Diadiushkin, Alexander; Sandkuhl, Kurt; Maiatin, Alexander

doi:10.7250/csimq.2019-20.04

Cited by 10 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, smartphones are increasingly playing a more significant role in ecommerce and online payments (Chen et al, 2019). Technologies have enabled digital transformation for businesses and payment transactions to occur within a day or instantaneously by improving the speed of the settlement processes (Chen et al, 2019;Diadiushkin et al, 2019;Eappen, 2019;Mugari, 2017;Park et al, 2019).…”

Section: Ecommerce Overviewmentioning

confidence: 99%

“…Payment security, in particular, is a significant and important concern for merchants and consumers (Chen et al, 2019). Cyber fraud incidents are the use of online criminal deception and theft intended to result in financial and/or personal gain (Diadiushkin et al, 2019;Park et al, 2019). Ecommerce fraud prevention relies on rule-based detection systems.…”

Section: Ecommerce Overviewmentioning

confidence: 99%

“…Ecommerce became a core competency for many retailers and merchants, but conducting transactions with e-payments became a critical issue due to fraud (T. Huang & Huang, 2019). Cyber fraud is online criminal deception and theft intended to result in financial and/or personal gain using Internet technologies (Diadiushkin et al, 2019;Park et al, 2019). Global ecommerce online payment fraud has resulted in an estimated $41 billion of losses (Statista, 2022).…”

Section: Ecommerce Fraud Incidentsmentioning

confidence: 99%

“…Many organizations have been combating ecommerce fraud with detection platforms with rule-based approaches (Diadiushkin et al, 2019;Kawase et al, 2019). A rules-based system is a special type of expert system consisting of if-then rules used for classification, regression, and association (Liu et al, 2016).…”

Section: Ecommerce Fraud Prevention Systemsmentioning

confidence: 99%

See 3 more Smart Citations

Ecommerce Fraud Incident Response: A Grounded Theory Study

Dwight

2023

IJIKM

View full text Add to dashboard Cite

Aim/Purpose: This research study aimed to explore ecommerce fraud practitioners’ experiences and develop a grounded theory framework to help define an ecommerce fraud incident response process, roles and responsibilities, systems, stakeholders, and types of incidents. Background: With a surge in global ecommerce, online transactions have become increasingly fraudulent, complex, and borderless. There are undefined ecommerce fraud roles, responsibilities, processes, and systems that limit and hinder cyber incident response to fraudulent activities. Methodology: A constructivist grounded theory approach was used to investigate and develop a theoretical foundation of ecommerce fraud incident response based on fraud practitioners’ experiences and job descriptions. The study sample consisted of 8 interviews with ecommerce fraud experts. Contribution: This research contributes to the body of knowledge by helping define a novel framework that outlines an ecommerce fraud incident response process, roles and responsibilities, systems, stakeholders, and incident types. Findings: An ecommerce fraud incident response framework was developed from fraud experts’ perspectives. The framework helps define processes, roles, responsibilities, systems, incidents, and stakeholders. The first finding defined the ecommerce fraud incident response process. The process includes planning, identification, analysis, response, and improvement. The second finding was that the fraud incident response model did not include the containment phase. The next finding was that common roles and responsibilities included fraud prevention analysis, tool development, reporting, leadership, and collaboration. The fourth finding described practitioners utilizing hybrid tools and systems for fraud prevention and detection. The fifth finding was the identification of internal and external stakeholders for communication, collaboration, and information sharing. The sixth finding is that research participants experienced different organizational alignments. The seventh key finding was stakeholders do not have a holistic view of the data and information to make some connections about fraudulent behavior. The last finding was participants experienced complex fraud incidents. Recommendations for Practitioners: It is recommended to adopt the ecommerce fraud response framework to help ecommerce fraud and security professionals develop an awareness of cyber fraud activities and/or help mitigate cyber fraud activities. Future Research: Future research could entail conducting a quantitative analysis by surveying the industry on the different components such as processes, systems, and responsibilities of the ecommerce fraud incident response framework. Other areas to explore and evaluate are maturity models and organizational alignment, collaboration, information sharing, and stakeholders. Lastly, further research can be pursued on the nuances of ecommerce fraud incidents using frameworks such as attack graph generation, crime scripts, and attack trees to develop ecommerce fraud response playbooks, plans, and metrics.

show abstract

Section: Ecommerce Overviewmentioning

confidence: 99%

Section: Ecommerce Overviewmentioning

confidence: 99%

Section: Ecommerce Fraud Incidentsmentioning

confidence: 99%

Section: Ecommerce Fraud Prevention Systemsmentioning

confidence: 99%

See 2 more Smart Citations

Ecommerce Fraud Incident Response: A Grounded Theory Study

Dwight

2023

IJIKM

View full text Add to dashboard Cite

show abstract

“…Recently, due to the powerful representation abilities of graphs as well as the advances in graph mining and learning techniques, Graphbased Anomaly Detection (GAD) is becoming prevalent across a wide spectrum of domains. Various GAD systems are proposed and deployed as an indispensable security component in detecting, for example, fake accounts in social networks [1], fraudulent transactions in the financial industry [2], and Botnets in communication networks [3].…”

Section: Introductionmentioning

confidence: 99%

BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection

Zhu¹,

Lai²,

Zhao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Graph-based Anomaly Detection (GAD) is becoming prevalent due to the powerful representation abilities of graphs as well as recent advances in graph mining techniques. These GAD tools, however, expose a new attacking surface, ironically due to their unique advantage of being able to exploit the relations among data. That is, attackers now can manipulate those relations (i.e., the structure of the graph) to allow some target nodes to evade detection. In this paper, we exploit this vulnerability by designing a new type of targeted structural poisoning attacks to a representative regression-based GAD system termed OddBall. Specifically, we formulate the attack against OddBall as a bi-level optimization problem, where the key technical challenge is to efficiently solve the problem in a discrete domain. We propose a novel attack method termed BinarizedAttack based on gradient descent. Comparing to prior arts, BinarizedAttack can better use the gradient information, making it particularly suitable for solving combinatorial optimization problems. Furthermore, we investigate the attack transferability of BinarizedAttack by employing it to attack other representation-learning-based GAD systems. Our comprehensive experiments demonstrate that BinarizedAttack is very effective in enabling target nodes to evade graph-based anomaly detection tools with limited attacker's budget, and in the black-box transfer attack setting, BinarizedAttack is also tested effective and in particular, can significantly change the node embeddings learned by the GAD systems. Our research thus opens the door to studying a new type of attack against security analytic tools that rely on graph data.

show abstract

Use of EA Models in Organizational AI Solution Development

Sandkuhl

Rittelmeyer

2022

Advances in Enterprise Engineering XV

View full text Add to dashboard Cite

Fraud Detection in Payments Transactions: Overview of Existing Approaches and Usage for Instant Payments

Cited by 10 publications

References 21 publications

Ecommerce Fraud Incident Response: A Grounded Theory Study

Ecommerce Fraud Incident Response: A Grounded Theory Study

BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection

Use of EA Models in Organizational AI Solution Development

Contact Info

Product

Resources

About