Sustainable response system building against insider-led cyber frauds in banking sector: a machine learning approach

Abstract

Purpose This paper aims to focus on the different types of insider-led cyber frauds that gained mainstream attention in recent large-scale fraud events involving prominent Indian banking institutions. In addition to identifying and classifying cyber fraud, the study maps them on a severity scale for optimal mitigation planning. Design/methodology/approach The methodology used for identification and classification is an analysis of a detailed literature review, a focus group discussion with risk and vigilance officers and cyber cell experts, as well as secondary data of cyber fraud losses. Through machine learning-based random forest, the authors predicted the future of insider-led cyber frauds in the Indian banking business and prioritized and predicted the same. The projected future reveals the dominance of a few specific cyber frauds, which will make it easier to develop a fraud mitigation model based on a victim-centric approach. Findings The paper concludes with a conceptual framework that can be used to ensure a sustainable cyber fraud mitigation ecosystem within the scope of the study. By using the findings of this research, policymakers and fraud investigators will be able to create a more robust environment for banks through timely detection of cyber fraud and prevent it appropriately before it happens. Research limitations/implications The study focuses on fraud, risk and mitigation from a victim-centric perspective and does not address it from the fraudster’s perspective. Data availability was a challenge. Banks are recommended to compile data that can be used for analysis both by themselves and other policymakers. Practical implications The structured, sustainable cyber fraud mitigation suggested in the study will provide an agile, quick, proactive, stakeholder-specific plan that helps to safeguard banks, employees, regulatory authorities, customers and the economy. It saves resources, cost and time for bank authorities and policymakers. The mitigation measures will also help improve the reputational status of the Indian banking business and prolong the banks’ sustenance. Originality/value The innovative cyber fraud mitigation approach contributes to the sustainability of a bank’s ecosystem quickly, proactively and effectively.

Internal-led cyber frauds in Indian banks: an effective machine learning–based defense system to fraud detection, prioritization and prevention

“…Fraud response systems should detect cyber frauds at the earliest (Dimitrijevic et al, 2017) and dynamically manage large amounts of data (Udeh and Ugwu, 2018). It should prioritize (Roy and Prabhakaran, 2022) and prevent fraud at its earliest stage (Braithwaite, 2010;Tamrin et al, 2017). Prioritizing frauds will enable timely and cost-efficient fraud mitigation measures for high-priority frauds.…”

“…Before presenting mitigation measures, the authors analyzed existing mitigation methods. According to (Roy and Prabhakaran, 2022), existing plans are either generic (Rohit et al, 2018), prevention-centric (Khanna and Arora, 2009) or limited to victim-affected stakeholders (employees, customers, regulators and banks). Authors recommend that the plan be proposed so that it not only prioritizes the frauds but also identifies the root cause of the problem as long-term mitigation.…”

“…Cyber fraud studies (Feily et al, 2009;Tamrin et al, 2017;Swaby, 2012) observed that criminals could exploit banks and perpetuate such crimes if they are internal systems entities that act as organized and well-connected communities. Previous studies (Roy and Prabhakaran, 2022;Roy and Basu, 2021a) focused on generic mitigation solutions that were less cost-effective for stakeholders. As cyber frauds continue to threaten the banking ecosystem, a more sophisticated, innovative and persuasive vigilance approach against the traditional silobased monitoring system is necessary to combat the dynamic cyber threat in the banking ecosystem.…”

“…Besides, European and Middle East banks (Eaton and Korach, 2016;Thompson et al, 2017) emphasized that fraud investigation measures must be flexible enough to respond to evolving crimes and detect change during fraud events. Authors emphasize an effective fraud response system that must be: simple to understand (Van Horenbeeck, 2018), easy to use (Nguyen and Pontell, 2017), agile (Roy and Prabhakaran, 2022) and provide mitigation in a more controlled and observed environment for quick response (Ma and McKinnon, 2021).…”

“…Attacks can range from simple password leaks to ransomware attacks, but over the past decade, fraud has increased significantly due to people within the internal banking ecosystem. Between 2012 and 2022, the percentage of frauds reported by internal employees in India has grown from 11.64% to 23.45% (Roy and Prabhakaran, 2022). Such rising statistics warn banking officials about internal discrepancies within their network.…”