Robust Financial Fraud Alerting System Based in the Cloud Environment

Abstract

The digitalisation of finance influenced the emergence of new technological concepts for existing user needs. Financial technology, or fintech, provides improved services for customers and new economic value for businesses. As such, fintech services require on-demand availability on a 24/7 basis. For this reason, they are often deployed in cloud environments that allow connectivity with ubiquitous devices. This allows customers to perform online transactions, which are overseen by the respective financial institutions. However, such cloud-based systems introduce new challenges for information security. On one hand, they represent attractive targets for cyberattacks. On the other, financial frauds can still go unnoticed by the financial institutions in charge. This paper contributes to both challenges by introducing the concept for a cloud-based system architecture for fraud detection and client profiling in the banking domain. Therefore, a systematic risk assessment was conducted in this context, and exploitation probabilities were inferred for multiple attack scenarios. In addition, formal verification was accomplished in order to determine the effects of successful vulnerability exploits. The consequences of such security violations are discussed, and considerations are given for improving the resilience of fintech systems.

Financial Fraud Detection Using Value-at-Risk With Machine Learning in Skewed Data

“…Regression analysis is utilized in the study [30] to look at how enterprises manage risk to determine how control environments, risk assessments, control activities, information and communication, and monitoring contributed to fraud prevention and detection efforts in Indonesian firms. The study [31] defined additional security attributes that might have an impact on the cloud system and carried out an anomaly detection based on risk assessment named parallel processing (PP) that covers cyber threats and exploitation likelihoods. The model checker is then employed to determine the risk exposure rates associated with the respective attacks.…”

Development of an efficient machine learning algorithm for reliable credit card fraud identification and protection systems

“…The outcomes of the experiments revealed that the system based on HMM is both successful and beneficial in understanding the spending profile of the cardholders they are associated with. Anomalies in Fintech systems were identified by deploying ML techniques [9]. It was determined to focus on the suspicious behavior in the financial database, and algorithms were developed to forecast future thefts.…”

Strengthening FinTech Defenses: A Novel Approach with Federated Learning and Anomaly Identification

“…The federated learning approach takes place in which models are trained from the distributed devices, such as complete data privacy, which has been ensured with no need for data to be transferred. The data-oriented protection models are finished by applying anomaly detection tools to detect abnormal data patterns or activities, which are the distinctive traits of security threats from distributed data 4 . With this technique, federated learning can be utilized with anomaly detection to meet the needed degree of scalability when dealing with vital and distributed data.…”