Leveraging artificial intelligence to mitigate money laundering risks through the detection of cyberbullying patterns in financial transactions

 Corresponding author: Shuvo Kumar Mallik. Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0. Leveraging artificial intelligence to mitigate money laundering risks through the detection of cyberbullying patterns in financial transactions Shuvo Kumar Mallik 1, *, Md. Raisul Islam 2, Imran Uddin 3, Md. Azam Ali 4 and Sadia Maliha Trisha 5 1 Department of Economics, Southeast University, Dhaka, Bangladesh. 2 Associate Professor, Department of Law and Land Administration, University of Rajshahi, Bangladesh. 3 A2Z Finance Australia (Easy Mortgage Solutions Australia), Australia. 4 Department of Marketing, Jagannath University, Dhaka, Bangladesh. 5 Dublin Business School, Dublin, Ireland. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 Publication history: Received on 10 December 2024; revised on 21 January 2025; accepted on 24 January 2025 Article DOI: https://doi.org/10.30574/gjeta.2025.22.1.0015 Abstract Money laundering (ML) is a vital source to clean the money from the financial system with illegal funds. Corruption, exploitation of a given community, drug use, and much more are all associated with it. Due to the massive number of transactions worldwide, detection of ML operations is complex. But it makes it possible for criminals to exploit financial systems to facilitate illicit transactions. This is primarily about reducing the risk that someone will be out of pocket because of money laundering. AIdriven applications of AML tools are now monitoring transactions to deal with it. In total, 112 research papers are reviewed (identified the gap in literature) which serves as a guide for the future direction of this research domain. The outcome of this systematic literature review effort will not only pave the way for the research community, also aid the state agencies to formulate an ideal AML ecosystem to tackle these prominent concerns while ensuring a healthy environment for their inhabitants. Those starting points can be taken to evaluate the current state of affairs from diverse perspectives and pave the way towards future research directions to explore and develop the high levels of authenticity and security that artificial intelligence (AI) can bring to the finance sector. Keywords: Money Laundering; AIDriven; Financial Systems; Artificial Intelligence (AI) 1. Introduction The ability of AI to automate functions that many have come to think of as “tedious” is yielding tremendous dividends, such as freeing up time for those seeking to collect money to do vital donor engagement and strategy. While the phrases may seem to read like generic buzz words, AI, data analytics and machine learning (ML) are being woven into organization technology systems as innovative approaches to challenges in risk management, human resources and compliance. Ageing-and-banking-sector Fraud: It is common for many industries to lose millions of dollars to fraud every year, including banking and financial institutions insurance companies, government agencies, telecommunication industries, and law enforcement (Jamshidi and Reza Hashemi 2012). We exist in a tradition that criminal circumstances against senior people are frequently rising. With the increasing level of dangers and incursions in society, desperation for a security system to help assure their wellbeing and safety is becoming more common. The opposite, global result in terms of cyber hazards (Suresh et al. 2020). It may pay off well to engage in criminal activities, like smuggling, bribery and drug trafficking. Illegally acquired money must be disguised as legitimate before it can be spent freely (Wang and Yang 2007). Fraud detection is a popular topic in the data mining community. Fraudulent transactions are often characterized by a high degree of sophistication. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 95 There are extremely unusual in a huge chunk of regular transactions, and manipulators are thoroughly planned and far dropped (Kunlin 2018). Detecting fraud can be a pretty hard job for a lot of businesses. Due to easy accessibility to personal information and sophisticated password cracking techniques, hackers can commit online fraud easily. In this case, customers lose billions of dollars each year due to online transaction fraud (Song 2020). The damage inflicted on the banks and their customers as a result of fraud has increased the need for fraud detection and prevention technology. Fraud detection systems are increasingly using AI and machine learning techniques (Erdoğan et al. 2020; Guevara, Garcia-Bedoya and Granados 2020). Hamid, Ali R. (2017). The National Law Review. It is the risk used for laundering illegal proceeds so it can be reinjected into the authorized financial system or used to fund other illegal activity (Ketenci et al. 2021). Money laundering is the process of switching dirty money to clean money. The money, for instance, comes from illegal activities such as human trafficking, kidnapping, hired assassination, bribes, tax evasion, and drug dealing. This is because an organization or an individual cannot deposit money directly into a bank, for the bank sees the transaction as anomalous, and the user cannot prove the origin of the money. This money is termed as “black money” which has an adverse effect on the economy. This is why the anti-money laundering regulations are rather stringent among the two sides of the coin, emerging and wealth countries (Samanta et al. 2019). ML is the practice of making illegal earned income appear to be legitimate, a process used by criminal offenders to hide the illegal origin and ownership of their criminally-obtained assets. It is now a serious threat to the financial system and the nation as a whole. This nefarious activity is becoming more sophisticated all the time, and, yes, has grown beyond the cliché of smuggling of drugs to include financing of terrorists and, of course, personal profit. Money laundering refers to the process of the act of criminals trying to disguise illegally obtained funds using of a legitimate source like as large investment or pension funds or investing in banking products (Le Khac, Markos, and Kechadi 2010). Money laundering is a huge metropolitan menace, and the identification of illegal financial transactions through ML applications is tough and time-consuming. However, most current anti-money laundering (AML) systems are limited to link analysis, networking analysis, risk scoring categorization and outlier detection to identify suspicious transactions (Thi et al. 2020). Re-attachment of a criminal analysis is a complicated operation, requiring to process large amount of data and from many data sources, for example from billings or from bank account activities, what collect information useful in the view of an investigator (Dreżewski, Sepielak, Filipkowski 2015). Definition. AML systems are used by financial institutes (e.g., banks and other credit-issuing institutions) for the purpose of combating money laundering by detecting risks, transactions, and potential money launderers (Han et al. 2020). The FAIS (AI System) of the American Financial Crime Enforcement Network utilized a combination of human intelligence and software agents to detect suspected ML across a large data landscape. The use of such computer analysis system in artificial intelligence can significantly increase work efficiency and is an important means for the development of anti-money laundering (AML) system (Wang and Yang 2007). AI is a phrase that has been used a lot in science fiction, but now it is more commonly known as it has become more part of our daily life. Some of the Fast-Retiring Sectors Include Transportation, Healthcare, Retail And Finance A word processor AI drive heuristically a pc with the exact features to animated a variety of individual-intellectual responsibilities, just as observing, making, thinking and difficulties in 1955. In modern era, various businesses have been developed with the help of AI applications (Guan, Mou and Jiang 2020). Money laundering has been identified since increased reporting of large transactions by financial institutions to the public department in 1970 (Soltani et al. 2016). Money laundering prevention systems are employed by financial institutions (banks and other credit suppliers do such) to fight money laundering (ML) which they do by ways of identification risks, transactions, and identifying money launderers (Han et al. 2020). These papers were reviewed to see if they: • List all the tools & channels used for ML in the financial sector; • Recognize proposed AI-based generic solutions to restrict money laundering; • Several indicators that denote the risk of money laundering; and • Explain the economic and social effects of ML on the society and on various financial sectors. This is mainly to mitigate the actual threats associated with ML. To counter this, antimoney laundering systems are relying on AI-driven apps that best track transactions. Main issues and concerns include the security and safety of the financial sector from ML. Embedding security into AI-based applications seems to be the solution for them to achieve this goal. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 96 The word ML confines to separating criminal proceeds from their sources; or to make money, earned through unlawful means, seem legal or clean (Bashir et al. 2020). It is also defined as “the process of moving illegally gained funds through a legitimate person or an account so that it can no longer be traced to its illegal source.” It is a worldwide issue that has caused political upheaval and impeded economic development. It remains a constant worry for many officials in many countries. There are several techniques that can be used to perform money laundering. The first is in the import and export sectors, which are routes through which money can be converted into goods and then exported or legitimately brought back into the country (Alnasser Mohammed 2021). The fight against money laundering has almost come to dominate the anti-crime policy agenda in recent years (Rusanov and Pudovochkin 2021). All human trafficking and acts of drug, bribery, extortion, kidnapping-forransom, terrorist financing, tax evasion, and others are indeed linked to ML (Ketenci et al. 2021). Due to its severity, it is receiving growing interest from scholars and governments worldwide. Partly, ML-related money represents a significant percentage of the global GDP each year (Xie et al. 2010). Such a huge, complex and deep underground market is nearly impossible to estimate exactly; around two trillion USD (International Monetary Fund (IMF) (Hunter and Biglaiser 2020)) are laundered every year through financial institutes around the world, securing ML the spot as one of the biggest markets in the world. 2021). Money laundering is believed to be worth around $3.2 trillion (or 3 percent of global GDP) per year according to the IMF. Earnings from money laundering are commonly used to finance criminal activities including illegal arms trading, drug trafficking, human trafficking and terrorist attacks (Han et al. 2020). The FIU (the Financial Intelligence Unit) receives reports from financial organizations on suspicious actions. FIU collects information from various financial sectors, both inside and outside the authority, and communicates to law enforcement authorities (LEA) when appropriate (Ketenci et al. 2021). Fraud detection is a crucial component in minimizing losses. Hard-hitting security software aren’t as the fraudsters conquer their invasion by evading with their rotten evasions and by making state-of-the-art fraudulent techniques. Fraud in bank is a type of federal offense that may include deceiving financial institutions to obtain a monetary benefit as a result of someone else's actions. Fraud costs banks and Fintech’s billions of dollars every year. Scams that have elements of bribery where bankers are lured to earn financial assets. Banks and insurance firm are a favorite target for fraudsters. They capture billions of dollars in financial resources every year. The common types of bank fraud are Credit and debit card fraud, False selling insurance, Money laundering, Account fraud (Sarma et al. 2020). Worldwide, there is a concerted global effort to defend these financial organizations from the increasing use by terrorists of nonprofit organizations (NPOs). In order to assist other countries in assessing the adequacy of their current laws and regulations concerning nonprofit organizations, the FATF (Financial Action Task Force) published Special Recommendation (SR) VIII (Molla Imeny et al. 2021; Omar, Johari, and Arshad 2014; Savona and Riccardi 2019). The performance of a country’s financial institution evaluates its compliance with the FATF 40 + 90 (Choo 2014) guidelines and a full evaluation report serves as the instrument to enable each country to draft its AML rules that comply with the system (Young and Woodiwiss 2021). Enhanced due diligence in the United States covers the monitoring of risky and terrorism-related funding and customer identification in high-risk jurisdictions and large banks’ transactions. This has lead to a dirigisme policythat suits many G20 submitting nations to collect and distribute information - crypto currency around the world may soon free banking bodies to be globally managed with vast amounts of alternative deposits and transactions that are growing outside the limits of needing to be identified by those participating in G20 and other 'good guys' within donation Terrorism or the AML/CFT system to completely harmonize globally collecting information on events/trends of terrorism finance especially in the poorer regions that have increasingly included less complicated solutions provided by banks (Bashir et al. 2020). Technologies in this space have given rise to a number of new challenges that regulators and others are playing catchup to respond to. Economic rationality can push people to commit acts of AI and to legitimize the operations of AI (Gudkov 2020). Due to conventional security breaches and the concerns over how firms handle personal data extracted from customers or ordinary users, Cybersecurity has become a fundamental subject. (2) One of the most basic principles of cybersecurity in banking transactions is the protection of client assets while meeting tight data privacy normative requirements. Not only technologically, but also legally and ethically, the development of AI poses many challenges (Nizioł 2021). It is considered a threat to jobs because it will replace manual labor. Financial services are under threat as well (Lee 2020). AI and machine learning are rapidly changing and shaping emerging nations political, economic, and social fabric. Consequently, experts believe that AI-based solutions will be a game-changer with significant implications for increasing financial inclusion of poor individuals (GarciaBedoya, Granados, and Cardozo Burgos 2021; Kshetri 2021). —It has become a crucial resource for big banks grappling with regulatory shifts, heightened anti-money laundering (AML) laws, and target-theft infiltration-prone consumers. Internet banking is convenient, but it also brings serious issues (Jullum et al. 2020). Concurrently, Internet banking security has collected the consideration of individuals from varying backgrounds Although many of day-to-day exchange of money is done in many non-cash payment methods (such as E-Cash, Debit/Credit cards, Mobile Payment Systems, etc.), but in many situations confidentiality and availability of payment information has been there. Such incidents can happen on the Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 97 client (funds owners) as well as the bank (or outlet) side and also, during the transfer of payment information in communication networks (Plaksiy, Nikiforov and Miloslavskaya 2018). 1.1. Research Protocol SLR is established method of identifying and evaluating research output relevant to a specific research question. SLR attempts to provide an unbiased assessment of a research problem by adopting a rigorous, reliable, and auditable process (Kitchenham 2004). SLR has been disseminated in several fields, such as FinTech, remittance (Hussain et al. 2020) and health care systems (Nazir et al. 2020). The objective of this SLR approach is to reconstruct the application of machine learning and AI in financial institutions to prevent the likelihood of money laundering. The following bullets show the key to explain this SLRs purpose: • Emission of the exploratory research and inquiry into previous studies of the technology. The above set of questions was formulated using the AI at hand, on the premise of providing high security and authentication mechanism in different fields of business to mitigate the threat of Machine learning. • To discover needs in technology that will cause further research These new domain will help the business sectors and its employees by providing great level of authentication for the security purposes to avoid money laundering. • All the selected articles from online libraries are the most suitable ones for this SLR work. (2) Researchers will critically evaluate the fundamental research articles in AI and ML fields. The SLR approach followed in this prospective research effort follows the proposed guidelines suggested by Kitchenham et al. (Keele 2007; Kitchenham et al. 2010). The process uses in this SLR review methodology is shown in figure 1. As shown in Figure 1, the review process comprises of seven important steps and all of the stages are described in detail. 2. Research Process Methodology Systematic literature review (SLR) emphasizes the vital aspects of pre-review processes (research question formulation, identifying keywords, error formulation in question selected by considering publication of the digital libraries available on the web for the inclusion/exclusion criteria for the original articles for the review process). The current systematic review was conducted due to the recent increase in the research interest associated with AI and money laundering. With a strong research approach and literature review knowledge in the area of AI-based AML systems in particular, the safety and security of the financial sector is assured. Figure 1 Purposed SLR procedure. 2.1. Research Question Identification Most importantly, having established research questions help to perform an SLR. Different characteristics of AI-based platform is critically examined and reported to ascertain the most appropriate research queries. This led to the formation of the five research questions in Table 1. SLR is yet another way of critically reviewing a situation. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 98 2.2. Formulation of Query Once the research question and keyword formulation from the selected online digital libraries were identified and finalized, the next step was to formulate query. Table 1 Selected research questions and corresponding explanation RQ1) What are the different tools and channels utilized for ML in the financial sector? ML is converting ‘dirty’ money to conceal the source of the cash. ML has become a significant issue in the global market. The primary object of this RQ is to identify the various methods used for machine learning in third-world countries. RQ2) What are the most AI-based generic solutions proposed for restricting ML? The aims of this RQ is to counter the various AI-based methods established to provide generic solutions for restricting ML. Furthermore, question is to present new direction to the research work which enhance the competencies of AI-based system and provide various solution to overcome the risk of ML. RQ3) What are the various components that can determine the risk money laundering? This research question identifies different types of embedded solutions proposed for real-time security analysis. RQ4) Using the literature as evidence, how can we minimize the risk factor of ML within financial sectors? Based on the literature, the prime object of this question is to increase the capabilities of existing AI based system within the financial sector to provide enhance security to count the risk of ML. RQ5) What are the economic and social impacts of money laundering on society? Aimis expending vastly in the global village. The aim of this RQ is explain the social and economic impacts of money laundering in the society. 2.3. Review Process The 112 articles were selected according to the defined criteria for SLR after screening the assigned online libraries for important primary articles and the inclusion and exclusion circulation. The final group of materials includes workshop papers, conference proceedings, book parts, journal pieces, and review/survey articles. During this phase, a voting schema was proposed. If a majority of the authors felt that the paper should be on this final list of the most relevant papers, it was included; otherwise, it was removed. From all these online digital libraries, four are selected as the most appropriate for gathering relevant research papers for this SLR process are Taylor & Francis, IEEE Xplore, Springer Link, and Elsevier. Table 2 summarizes the entire inclusion process. Review and assessment of 112 research articles have been completed. Figure 2 below shows the total number of publications from the identified peer-reviewed digital online libraries that added publications to this final pool. Table 2 Selection of articles for final development process. Digital Library Total articles Filtered articles Final selected articles IEEE 212 91 35 Elsevier 234 111 22 Taylor & Francis 221 76 24 Springer Link 311 56 21 Total 112 Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 99 Figure 2 Collection of online libraries for articles A total of 112 articles are fetched based on the defined criteria for SLR after scanning the specified online libraries for suitable primary articles and implementing the inclusion and exclusion sequence. The final pool of materials consists of workshop papers, conference proceedings, parts of books or long articles like journal papers, review/survey papers. During this stage, a voting mechanism was suggested. If the paper was deemed a good fit by more than half of the writers, it made the final list of the most relevant papers; otherwise, it was excluded. For this purpose, the four most relevant online digital libraries that will help to collect relevant research papers for this SLR process are chosen, which are Taylor & Francis, IEEE Xplore, Springer Link, and Elsevier. An overview of the entire inclusion process can be found in Table 2. We have compiled and indexed 112 publications for review and scoring. Figure 2 below shows the total number of publications using the selected peer reviewed digital online libraries that culminated the final pool. 2.4. Quality Assessment To assess the papers’ relevancy to the SLR protocol, we followed the criteria given in the SLR protocol. We evaluated all the RQs and the respective criteria proposed in the study against relevant papers (Khan, Nazir and Khan 2021). Figure 3 Contribution percentage for each library Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 100 Figure 4 Year-wise contribution of selected articles. Such evaluation ensured the quality of each SLR paper. In addition, all study topics were weighted based on the following criteria: • If a certain research article completely fulfilled that research question then it was given a weighted value of 1 • If an article was neither fully or partially fulfilled that research question then it was assigned a weighted value of 0.5, otherwise 0 Node weights were calculated by aggregating the values corresponding to relevant articles based on the varied research topics in the quality assessment; and further, while the leaf nodes are the weighted values of their research topics, the terminal node is the calculated mean value that expresses the input of the procedure for evaluation as depicted in Figure 5. The most significant circular shape means the higher the relevance of a given research paper to the research subject under examination in this SLR paper. 3. Analysis and Results Each question is then followed by insights that retrieve information on each proposed research area made for the current SLR study. Each of the keys below relates specifically to each associated research topic posed in the current SLR study. 3.1. RQ1) Which Tools and Channels are Being Used for Money Laundering in the Financial Sector? Now a day’s ML is becoming one of the serious threats for the banking sector. The banking sectors (Villar and Khan 2021) are having harsh penalty on customers for incompetent ML risk assessment like it happened to HSBC Bank London, which was charged about USD $2 billion by a US regulator for negligence to prevent Mexican drug criminal to launder using banking channel (Isa et al. 2015). There are multiple ways it can be done. They can mask the origins of their money by goading its way into real estate, casinos and inflated legal bills. ML methods typically cover three steps; layering, integration, and placement (Mahootiha, Golpayegani and Sadeghian 2021; Matanky-Becker and Cockbain 2021; Philippson 2001; Seymour 2008). For more than 30 years, legislators and stakeholders have enacted ML-related laws and regulations throughout the world. Placement is the method of injecting dirty money into the financial industry. However, layering is a method of executing complex transactions to hide the origin of funds. Lastly, integration means pulling funds out of a dedicated bank account. When layering is sophisticated, AML instruments are confused (Soltani et al. 2016). Table 3 briefly explains the various used tools for ML as below. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 101 Figure 5 Representation the relevant articles. 3.2. RQ2) What Are the Most AI-Based Generic Solutions Applied to Restrict Money Laundering? And every year, ML is a threat to the world economy. “Such proceeds could be reinvested into further criminal activity and pose a threat to the integrity of international financial systems. For this reason, many countries regard money laundering as a significant threat. This research question implies various generic approaches presented in the papers on constraining ML. The focus of this research question provides a background of the various AI based methods and approaches that can be used for mitigating money laundering. There is a series of proposed solutions to these problems, which can be seen in table 4. 3.3. RQ3) What are the different components that can identify / determine money laundering risk? Terrorist organizations depend on funds and illicit financing to sustain themselves. Without a constant and reliable source of funding, terrorist groups would be unable to manage daily paperwork, feed their members, or undertake operations (Fletcher, Larkin, and Corbet 2021). Other researchers had used different AI methods to strengthen ML ability. Technological advancements have transformed the finance industry in such a way as to reduce the risks of ML. The main objective of this RQ is to enunciate the different elements that may characterize the risk of money-laundering. Table 5: Description of various components influencing ML. 3.4. RQ4) How Do Financial Sectors Avoid Money Laundering as a Risk — as per the Literature? Since the 9/11 terrorist attack of 2001, the US has adopted a heightened sensitivity to movements of illegal money, owing to the belief that such networks facilitate global terrorist and criminal activity (Ferwerda et al. 2013). The spread of the internet has allowed for online financial transactions on everything from mobile device to PCs and even similar devices. There are many intermediary nodes in the network through which any user’s action in gaining access to the financial services must go through. Table 3 Different tools used for Money Laundering. S.No Channels selected for Money Laundering Description References 1. Social Network The suggested strategy presents an (Dreżewski, Sepielak, and Filipkowski 2015; efficient method to update the social Jamshidi and Reza Hashemi 2012; network since one of the obstacles of Mahootiha, Golpayegani, and a real-world electronic transaction Sadeghian 2021; Shaikh, Al-Shamli, and system is the vast volume of data and Nazir 2021) users. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 102 2. Credit Card Credit cards have become one of the most (Erdoğan et al. 2020; Sarma et al. 2020) popular onsite and online purchasing payments due to their simplicity of use. Due to the demand for credit cards rising, a slew of new fraud techniques, including as identity theft and phishing, arise to steal money from credit card scammers 3. Banking This paper describes the Anomaly-based (Al-Nuemat 2013; Mishra and Yadav 2020) Intrusion Detection Systems for AIDS for attack exposure. Intrusion Detection Systems IDS is implemented in research field in AI and various machine learning algorithms. 4. Digital Stolen Funds According to the findings, cybercrime is particularly in paying out electronic stolen monies, which they accomplish predominantly through money mules and virtual casinos. (Mikhaylov and Frank 2016) 5. Security and safety The study covers decision-making about critical infrastructure safety, with perceptions about unintentional risk serving as a corresponding point of debate. (Dai and Boroomand 2021; Guzman et al. 2016; Kose and Vasant 2017; Link et al. 2018; Rindell and Holvitie 2019; Srivastava, Bisht, and Narayan 2017) 6. Network attack The paper analysis the possibility of network attacks and promotes the development of artificial intelligence. (Shu et al. 2020) 7. Online Transactions This research looks at the effectiveness of reporting doubtful transaction made to a FIU (Financial intelligence unit) to prevent ML. (Dalla Pellegrina et al. 2020; Singla 2021; Xia et al. 2021) 8. Account The paper’s focuses on identifying every questionable ML account. Further in contrast, digs deeper into the highly suspicious ones to improve the recall and precision of ML account identification. (Tai and Kan 2019) 9. Employee dishonest The study proposed a model for criminals to compete against one another in a market but collaborate with other criminals and employee’s dishonesty in an engage to launder their criminal activity to process through change ML linkages (Imanpour et al. 2019) 10. Pressure Policies The consequences of political pressure to (Picard and Pieretti 2011) offshore financial hubs with the capacity to enforce compliance with AML legislation are discussed in this study. 11. Illicit Incomes Estimates of illegal revenue from drug (Loayza, Villa, and Misas 2019) trafficking and general crime are significant components of the dataset assembled in the article. Channels selected for Money Laundering Description References 12. Smuggling This article focuses on preventing a transnational criminal organization’s (TCO) interconnected contraband smuggling, money and money laundering (ICSML) networks. (Shen et al. 2021) 13. Criminal bargain This study reviews about the professional money laundering and examines how the launderer and the criminal negotiate a fee for the moneylaundering service. (McCarthy, van Santen, and Fiedler 2015) 14. Non-Profit organization The entire assessment adds to the body of knowledge on terrorist use of nongovernmental organizations (NPOs) while (Omar, Johari, and Arshad 2014) Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 109 from different angles and to propose potential lines of research to conduct the study and construct high levels of authenticity and security in the financial sector by using AI. To overcome this concern SLR has been performed analyzing for high security, authentication, and safety the best articles gathered from online peer-reviewed digital libraries. Compliance with ethical standards Acknowledgments The authors are grateful to the anonymous referees of journal for their extremely useful suggestion to improve the quality of the article. Disclosure of conflict of interest The author declared no potential conflicts of interest with respect to the research, authorship and publication of this article. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results. References [1] Al Hammadi, A., I. A. Zualkernan, and R. Ahmed. 2007. Impediments to adoption of e-Learning technology in combating anti-money laundering in UAE banks. Paper read at Seventh IEEE International Conference on Advanced Learning Technologies (ICALT 2007), Niigata, Japan. [2] Alkhalili, M., M. H. Qutqut, and F. Almasalha. 2021. Investigation of applying machine learning for watch-list filtering in anti-money laundering. Institute of Electrical and Electronics Engineers Access 9:18481–96. [3] Alnasser Mohammed, S. A. S. 2021. Money laundering in selected emerging economies: Is there a role for banks? Journal of Money Laundering Control 24 (1):102–10. [4] Al-Nuemat, A. A. 2013. Money laundering and banking secrecy in the Jordanian legislation. Journal Information and Communications Technology 34 (9):91–104. [5] Al-Rashidi, K. S. 2021. Indirect method of proof’and the Kuwaiti anti-money laundering law: a lesson from the UK. Paper read at Criminal Law Forum. [6] Bashir, R., R. Rajeev, A. Shatarah, and N. Bashir. 2020. A risk score analysis related to money laundering in financial institutions across nations. Paper read at 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Noida, India. [7] Butler, S. 2019. Criminal use of cryptocurrencies: A great new threat or is cash still king? Journal of Cyber Policy 4 (3):326–45. [8] Campbell-Verduyn, M. 2018. Bitcoin, crypto-coins, and global anti-money laundering governance. Crime, Law, & Social Change 69 (2):283–305. [9] Canhoto, A. I. 2021. Leveraging machine learning in the global fight against money laundering and terrorism financing: An affordances perspective. Journal of Business Research 131:441–52. [10] Chen, Y., and X. Han. 2021. CatBoost for fraud detection in financial transactions. Paper read at 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE), Guangzhou, China. [11] Chen, Z., L. D. Van Khoa, E. N. Teoh, A. Nazir, E. K. Karuppiah, and K. S. Lam. 2018. Machine learning techniques for anti-money laundering (AML) solutions in suspicious transaction detection: A review. Knowledge and Information Systems 57 (2):245–85. [12] Choi, D., and K. Lee. 2018. An AIapproach to financial fraud detection under IoT environment: A survey and implementation. Security and Communication Networks 2018:15. [13] Choo, K.-K. R. 2014. Designated non-financial businesses and professionals: A review and analysis of recent financial action task force on money laundering mutual evaluation reports. Security Journal 27 (1):1–26. [14] Dai, D., and S. Boroomand. 2021. A review of AIto enhance the security of big data systems: state-of-art, methodologies, applications, and challenges. Archives of Computational Methods in Engineering 29:1–19. [15] Dalla Pellegrina, L., G. Di Maio, D. Masciandaro, and M. Saraceno. 2020. Organized crime, suspicious transaction reporting and anti-money laundering regulation. Regional Studies 54 (12):1761–75. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 110 [16] Desmond, D., P. Salmon, and D. Lacey. 2021. Functional systems within cryptolaundering processes: A work domain analysis model of cryptolaundering activities. Journal of Cyber Policy 6 (2):155–76. [17] Dhaya, A., and R. Ravi. 2021. Multi feature behavior approximation model based efficient botnet detection to mitigate financial frauds. Journal of Ambient Intelligence and Humanized Computing 12 (3):3799–806. [18] Domashova, J., and N. Mikhailina. 2021. Usage of machine learning methods for early detection of money laundering schemes. Procedia Computer Science 190:184–92. [19] Dreżewski, R., G. Dziuban, Ł. Hernik, and M. Pączek. 2015. Comparison of data mining techniques for money laundering detection system. Paper read at 2015 International Conference on Science in Information Technology (ICSITech). [20] Dreżewski, R., J. Sepielak, and W. Filipkowski. 2012. System supporting money laundering detection. Digital Investigation 9 (1):8–21. [21] Dreżewski, R., J. Sepielak, and W. Filipkowski. 2015. The application of social network analysis algorithms in a system supporting money laundering detection. Information Sciences 295:18–32. [22] Erdoğan, Í., O. Kurto, A. Kurt, and Ş. Bahtıyar. 2020. A new approach for fraud detection with artificial intelligence. Paper read at 2020 28th Signal Processing and Communications Applications Conference (SIU), Gaziantep, Turkey. [23] Ferwerda, J., M. Kattenberg, H.-H. Chang, B. Unger, L. Groot, and J. A. Bikker. 2013. Gravity models of trade-based money laundering. Applied Economics 45 (22):3170–82. [24] Ferwerda, J., and E. R. Kleemans. 2019. Estimating money laundering risks: An application to business sectors in the Netherlands. European Journal on Criminal Policy and Research 25 (1):45–62. [25] Fletcher, E., C. Larkin, and S. Corbet. 2021. Countering money laundering and terrorist financing: A case for bitcoin regulation. Research in International Business and Finance 56:101387. [26] Gao, S., D. Xu, H. Wang, and Y. Wang. 2006. Intelligent anti-money laundering system. Paper read at 2006 IEEE International Conference on Service Operations and Logistics, and Informatics, Shanghai, China. [27] Garcia-Bedoya, O., O. Granados, and J. Cardozo Burgos. 2021. AI against money laundering networks: The Colombian case. Journal of Money Laundering Control 24 (1):49–62. doi:10. 1108/JMLC-04-2020-0033 . [28] Goldbarsht, D. 2020. Am I my corporate’s keeper? Anti-money laundering gatekeeping opportunities of the corporate legal officer. International Journal of the Legal Profession 29:1–20. [29] Gowin, K. D., D. Wang, S. Rakesh Jory, R. Houmes, and T. Ngo. 2021. Impact on the firm value of financial institutions from penalties for violating anti-money laundering and economic sanctions regulations. Finance Research Letters 40:101675. [30] Guan, C., J. Mou, and Z. Jiang. 2020. Artificial intelligence innovation in education: A twenty-year data-driven historical analysis. International Journal of Innovation Studies 4:134–47. [31] Gudkov, A. 2020. On Fiduciary Relationship with AISystems. The Liverpool Law Review 41 (3):251–73. [32] Guevara, J., O. Garcia-Bedoya, and O. Granados. 2020. Machine learning methodologies against money laundering in non-banking correspondents. Paper read at Applied Informatics: Third International Conference, ICAI 2020, Ota, Nigeria, October 29–31, 2020, Proceedings 3. [33] Guzman, A., S. Ishida, E. Choi, and A. Aoyama. 2016. Artificial intelligence improving safety and risk analysis: A comparative analysis for critical infrastructure. Paper read at 2016 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Bali, Indonesia. [34] Haffke, L., M. Fromberger, and P. Zimmermann. 2020. Cryptocurrencies and anti-money laundering: The shortcomings of the fifth AML Directive (EU) and how to address them. Journal of Banking Regulation 21 (2):125– 38. [35] Hamid, O. H. 2017. Breaking through opacity: A context-aware data-driven conceptual design for a predictive anti money laundering system. Paper read at 2017 9th IEEE-GCC conference and exhibition (GCCCE), Manama, Bahrain. [36] Han, J., Y. Huang, S. Liu, and K. Towey. 2020. Artificial intelligence for anti-money laundering: A review and extension. Digital Finance 2 (3):211–39. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 111 [37] Hong, X., H. Liang, Z. Gao, and H. Li. 2017. An adaptive resource allocation model in anti-money laundering system. Peer-To-Peer Networking and Applications 10 (2):315–31. [38] Huang, D., D. Mu, L. Yang, and X. Cai. 2018. CoDetect: Financial fraud detection with anomaly feature detection. Institute of Electrical and Electronics Engineers Access 6:19161–74. [39] Hunter, L. Y., and G. Biglaiser. 2020. The effects of the international monetary fund on domestic terrorism. Terrorism and Political Violence 34: 1–25. [40] Hussain, A., S. Nazir, S. Khan, and A. Ullah. 2020. Analysis of PMIPv6 extensions for identifying and assessing the efforts made for solving the issues in the PMIPv6 domain: A systematic review. Computer Networks 179:107366. [41] Imanpour, M., S. Rosenkranz, B. Westbrock, B. Unger, and J. Ferwerda. 2019. A microeconomic foundation for optimal money laundering policies. International Review of Law and Economics 60:105856. [42] Isa, Y. M., Z. Mohd Sanusi, M. Nizal Haniff, and P. A. Barnes. 2015. Money laundering risk: From the bankers’ and regulators perspectives. Procedia Economics and Finance 28:7–13. [43] Jakobi, A. P. 2018. Governing illicit finance in transnational security spaces: The FATF and anti-money laundering. Crime, Law, & Social Change 69 (2):173–90. [44] Jamshidi, S., and M. Reza Hashemi. 2012. An efficient data enrichment scheme for fraud detection using social network analysis. Paper read at 6th International Symposium on Telecommunications (IST), Tehran, Iran. [45] Jayantilal, S., S. Ferreira Jorge, and A. Ferreira. 2017. Portuguese anti-money laundering policy: A game theory approach. European Journal on Criminal Policy and Research 23 (4):559–74. [46] Jayasree, V., and R. V. Siva Balan. 2017. Money laundering regulatory risk evaluation using bitmap index-based decision tree. Journal of the Association of Arab Universities for Basic & Applied Sciences 23:96–102. [47] Jullum, M., A. Løland, R. Bang Huseby, G. Ånonsen, and J. Lorentzen. 2020. Detecting money laundering transactions with machine learning. Journal of Money Laundering Control 23 (1):173–86. [48] Keele, S. 2007. Guidelines for performing systematic literature reviews in software engineering. [49] UK: Citeseer.  [50] Ketenci, U. G., T. Kurt, S. Önal, C. Erbil, S. Aktürkoglu, and H. Şerban İlhan. 2021. A time-frequency based suspicious activity detection for anti-money laundering. Institute of Electrical and Electronics Engineers Access 9:59957–67. [51] Khan, S., S. Nazir, and H. Ullah Khan. 2021. Analysis of navigation assistants for blind and visually impaired people: A systematic review. IEEE Access 9:26712–26734. doi:10.1109/ ACCESS.2021.3052415 . [52] Kitchenham, B. 2004. Procedures for performing systematic reviews. Keele, UK, Keele University 33 (2004):1–26. [53] Kitchenham, B., R. Pretorius, D. Budgen, O. P. Brereton, M. Turner, M. Niazi, and S. Linkman. 2010. Systematic literature reviews in software engineering–a tertiary study. Information and Software Technology 52 (8):792– 805. [54] Kose, U., and P. Vasant. 2017. Fading intelligence theory: A theory on keeping AIsafety for the future. Paper read at 2017 International AIand Data Processing Symposium (IDAP). [55] Kruisbergen, E. W., E. R. Leukfeldt, E. R. Kleemans, and R. A. Roks. 2019. Money talks money laundering choices of organized crime offenders in a digital age. Journal of Crime & Justice 42 (5):569–81. [56] Kshetri, N. 2021. The role of AIin promoting financial inclusion in developing countries. Journal of Global Information Technology Management. [57] Kunlin, Y. 2018. A memory-enhanced framework for financial fraud detection. Paper read at 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA. [58] Kurshan, E., H. Shen, and H. Yu. 2020. Financial crime & fraud detection using graph computing: Application considerations & outlook. Paper read at 2020 Second International Conference on Transdisciplinary AI (TransAI). [59] Kute, D. V., B. Pradhan, N. Shukla, and A. Alamri. 2021. Deep learning and explainable AItechniques applied for detecting money laundering–a critical review IEEE Access, Irvine, CA, USA. [60] Lawlor-Forsyth, E., and M. Michelle Gallant. 2018. Financial institutions and money laundering: A threatening relationship? Journal of Banking Regulation 19 (2):131–48. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 112 [61] Lee, J. 2020. Access to finance for AIregulation in the financial services industry. European Business Organization Law Review 21 (4):731–57. [62] Le Khac, N. A., S. Markos, and M.-T. Kechadi. 2010. A data mining-based solution for detecting suspicious money laundering cases in an investment bank. Paper read at 2010 Second International Conference on Advances in Databases, Knowledge, and Data Applications, Menuires, France. [63] Link, J., K. Waedt, I. Ben Zid, and X. Lou. 2018. Current Challenges of the Joint Consideration of Functional Safety & Cyber Security, Their Interoperability and Impact on Organizations: How to Manage RAMS+ S (Reliability Availability Maintainability Safety+ Security). Paper read at 2018 12th International Conference on Reliability, Maintainability, and Safety (ICRMS), Shanghai, China. [64] Loayza, N., E. Villa, and M. Misas. 2019. Illicit activity and money laundering from an economic growth perspective: A model and an application to Colombia. Journal of Economic Behavior and Organization 159:442– 87. [65] Mabunda, S. 2018. Cryptocurrency: The new face of cyber money laundering. Paper read at 2018 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD), Durban, South Africa. [66] Maguchu, P. 2018. Revisiting money-laundering legislation in Zimbabwe and the role of international organisations. African Security Review 27 (3–4):278–90. [67] Mahootiha, M., A. H. Golpayegani, and B. Sadeghian. 2021. Designing a new method for detecting money laundering based on social network analysis. Paper read at 2021 26th International Computer Conference, Tehran, Iran, Computer Society of Iran (CSICC). [68] Marat, E. 2015. Global money laundering and its domestic political consequences in Kyrgyzstan. Central Asian Survey 34 (1):46–56. [69] Matanky-Becker, R., and E. Cockbain. 2021. Behind the criminal economy: Using UK tax fraud investigations to understand money laundering myths and models. Crime, Law, & Social Change 77:1–25. [70] McCarthy, K. J., P. van Santen, and I. Fiedler. 2015. Modeling the money launderer: Microtheoretical arguments on anti-money laundering policy. International Review of Law and Economics 43:148–55. [71] Mikhaylov, A., and R. Frank. 2016. Cards, money and two hacking forums: An analysis of online money laundering schemes. Paper read at 2016 European intelligence and security informatics conference (EISIC), Uppsala, Sweden. [72] Mishra, A., and P. Yadav. 2020. Anomaly-based IDS to detect attack using various AI& machine learning algorithms: A review. Paper read at 2nd International Conference on Data, Engineering and Applications (IDEA), Bhopal, India, February 28–29, 2020. [73] Molla Imeny, V., S. D. Norton, M. Salehi, and M. Moradi. 2021. Perception versus reality: Iranian banks and international anti-money laundering expectations. Journal of Money Laundering Control 24 (1):63–76. doi:10.1108/JMLC-06-2020-0064 . [74] Möser, M., R. Böhme, and D. Breuker. 2013. An inquiry into money laundering tools in the Bitcoin ecosystem. Paper read at 2013 APWG eCrime researcher’s summit. [75] Nazir, S., S. Khan, H. U. Khan, S. Ali, I. García-Magariño, R. Binti Atan, and M. Nawaz. 2020. A comprehensive analysis of healthcare big data management, analytics and scientific programming. Institute of Electrical and Electronics Engineers Access 8:95714–33. [76] Nikkel, B. 2020. Fintech forensics: Criminal investigation and digital evidence in financial technologies. Forensic Science International: Digital Investigation 33:200908. [77] Nizioł, K. 2021. The challenges of consumer protection law connected with the development of AIon the example of financial services (chosen legal aspects. Procedia Computer Science 192:4103–11. [78] Omar, N., Z. Amirah Johari, and R. Arshad. 2014. Money laundering–FATF special recommendation VIII: A review of evaluation reports. Procedia-Social and Behavioral Sciences 145:211–25. [79] Omar, N., R. Juhaida Johari, and M. Sathye. 2015. Malaysian DNFBPs’ perceptions on awareness, perceived impact and views on the AML/CFT requirements. Procedia Economics and Finance 31:595–600. [80] Philippson, S. 2001. Money laundering on the internet. Computers & Security 20 (6):485–485. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 113 [81] Picard, P. M., and P. Pieretti. 2011. Bank secrecy, illicit money and offshore financial centers. Journal of Public Economics 95 (7–8):942–55. [82] Plachouras, V., and J. L. Leidner. 2015. Information extraction of regulatory enforcement actions: From antimoney laundering compliance to countering terrorism finance. Paper read at Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015, Paris, France. [83] Plaksiy, K., A. Nikiforov, and N. Miloslavskaya. 2018. Applying big data technologies to detect cases of money laundering and counter financing of terrorism. Paper read at 2018 6th International Conference on Future Internet of Things and Cloud Workshops (FiCloudW), Barcelona, Spain. [84] Pol, R. F. 2020. Anti-money laundering: The world’s least effective policy experiment? Together, we can fix it. Policy Design and Practice 3 (1):73–94. [85] Pourhabibi, T., K.-L. Ong, B. H. Kam, and Y. Ling Boo. 2020. Fraud detection: A systematic literature review of graph-based anomaly detection approaches. Decision Support Systems 133:113303. [86] Premti, A., M. Jafarinejad, and H. Balani. 2021. The impact of the Fourth Anti-Money Laundering Directive on the valuation of EU banks. Research in International Business and Finance 57:101397. [87] Rindell, K., and J. Holvitie. 2019. Security risk assessment and management as technical debt. Paper read at 2019 International Conference on Cyber Security and Protection of Digital Services (Cyber Security), Oxford, UK, June 3–4, 2019. [88] Romero, V. 2020. Bloody investment: Misaligned incentives, money laundering and violence. Trends in Organized Crime 25:1–29. [89] Rudner, M. 2010. Hizbullah terrorism finance: Fund-raising and money-laundering. Studies in Conflict & Terrorism 33 (8):700–15. [90] Rusanov, G., and Y. Pudovochkin. 2021. Money laundering in the modern crime system. Journal of Money Laundering Control 24 (4):860–68. [91] Samanta, S., B. Kumar Mohanta, S. Prasad Pati, and D. Jena. 2019. A framework to build user profile on cryptocurrency data for detection of money laundering activities. Paper read at 2019 International Conference on Information Technology (ICIT). [92] Sarma, D., W. Alam, I. Saha, M. Nazmul Alam, M. J. Alam, and S. Hossain. 2020. Bank fraud detection using community detection algorithm. Paper read at 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India. [93] Savona, E. U., and M. Riccardi. 2019. Assessing the risk of money laundering: Research challenges and implications for practitioners. European Journal on Criminal Policy and Research 25 (1):1–4. [94] Seymour, B. 2008. Global money laundering. Journal of Applied Security Research 3 (3–4):373–87. [95] Shaikh, A. K., M. Al-Shamli, and A. Nazir. 2021. Designing a relational model to identify relationships between suspicious customers in anti-money laundering (AML) using social network analysis (SNA). Journal of Big Data 8 (1):1–22. [96] Shehu, A. Y. 2012. Promoting financial inclusion for effective anti-money laundering and counter financing of terrorism (AML/CFT). Crime, Law, & Social Change 57 (3):305–23. [97] Shen, Y., T. C. Sharkey, B. K. Szymanski, and W. Al Wallace. 2021. Interdicting interdependent contraband smuggling, money and money laundering networks. Socio-Economic Planning Sciences 78:101068. [98] Shu, F., S. Chen, F. Li, J. Zhang, and J. Chen. 2020. Research and implementation of network attack and defense countermeasure technology based on AItechnology. Paper read at 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China. [99] Singh, K., and P. Best. 2019. Anti-money laundering: Using data visualization to identify suspicious activity. International Journal of Accounting Information Systems 34:100418. [100] Singla, J. 2021. Comparing ROC curve based thresholding methods in online transactions fraud detection system using deep learning. Paper read at 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS). [101] Sittlington, S., and J. Harvey. 2018. Prevention of money laundering and the role of asset recovery. Crime, Law, & Social Change 70 (4):421–41. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 114 [102] Sobh, T. S. 2020. An intelligent and secure framework for anti-money laundering. Journal of Applied Security Research 15 (4):517–46. [103] Soltani, R., U. Trang Nguyen, Y. Yang, M. Faghani, A. Yagoub, and A. An. 2016. A new algorithm for money laundering detection based on structural similarity. Paper read at 2016 IEEE 7th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York, NY, USA. [104] Song, Z. 2020. A data mining based fraud detection hybrid algorithm in E-bank. Paper read at 2020 International Conference on Big Data, AIand Internet of Things Engineering (ICBAIE), Fuzhou, China. [105] Srivastava, S., A. Bisht, and N. Narayan. 2017. Safety and security in smart cities using artificial intelligence—A review. Paper read at 2017 7th International Conference on Cloud Computing, Data Science & EngineeringConfluence. [106] Stokes, R. 2012. Virtual money laundering: The case of Bitcoin and the Linden dollar. Information & Communications Technology Law 21 (3):221–36. [107] Suresh, A., A. P. Subeer, A. Mary Philip, J. Shaji Varughese, and J. Mathew. 2020. Comprehensive home security for elderly people using IoT and artificial intelligence. Paper read at 2020 IEEE International Conference for Innovation in Technology (INOCON), Bangluru, India. [108] Tai, C.-H., and T.-J. Kan. 2019. Identifying money laundering accounts. Paper read at 2019 International Conference on System Science and Engineering (ICSSE), Dong Hoi, Vietnam. [109] Thi, M. H., C. Withana, N. Thi Huong Quynh, and N. Tran Quoc Vinh. 2020. A novel solution for anti-money laundering system. Paper read at 2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA), Sydney, Australia. [110] Tropina, T. 2014. Fighting money laundering in the age of online banking, virtual currencies and internet gambling. Paper read at Era Forum. [111] Truby, J., R. Brown, and A. Dahdal. 2020. Banking on AI: Mandating a proactive approach to AI regulation in the financial sector. Law and Financial Markets Review 14 (2):110–20. [112] Turki, M., A. Hamdan, R. Thomas Cummings, A. Sarea, M. Karolak, and M. Anasweh. 2020. The regulatory technology “RegTech” and money laundering prevention in Islamic and conventional banking industry. Heliyon 6 (10):e04949. doi:10.1016/j.heliyon. 2020.e04949 . [113] Unger, B., and J. Den Hertog. 2012. Water always finds its way: Identifying new forms of money laundering. Crime, Law, & Social Change 57 (3):287–304. [114] Villar, A. S., and N. Khan. 2021. Robotic process automation in banking industry: A case study on Deutsche Bank. Journal of Banking and Financial Technology 5 (1):71–86. [115] Von Solms, J. 2021. Integrating Regulatory Technology (RegTech) into the digital transformation of a bank Treasury. Journal of Banking Regulation 22 (2):152–68. [116] Wang, S.-N., and J.-G. Yang. 2007. A money laundering risk evaluation method based on decision tree. Paper read at 2007 International conference on machine learning and cybernetics. [117] Watkins, R. C., K. M. Reynolds, R. Demara, M. Georgiopoulos, A. Gonzalez, and R. Eaglin. 2003. Tracking dirty proceeds: Exploring data mining technologies as tools to investigate money laundering. Police Practice & Research 4 (2):163–78. [118] Weber, J., and E. W. Kruisbergen. 2019. Criminal markets: The dark web, money laundering and counterstrategies-An overview of the 10th Research Conference on Organized Crime. Trends in Organized Crime 22 (3):346–56. [119] Xia, P., Z. Ni, H. Xiao, X. Zhu, and P. Peng. 2021. A novel spatiotemporal prediction approach based on graph convolution neural networks and long short-term memory for money laundering fraud. Arabian Journal for Science & Engineering 47:1–17. [120] Xie, P., J. H. Li, X. Ou, P. Liu, and R. Levy. 2010. Using Bayesian networks for cyber security analysis. Paper read at 2010 IEEE/IFIP International Conference on Dependable Systems & Networks (DSN), Chicago, IL. [121] Young, M. A., and M. Woodiwiss. 2021. A world fit for money laundering: The Atlantic alliance’s undermining of organized crime control. Trends in Organized Crime 24 (1):70–95. Global Journal of Engineering and Technology Advances, 2025, 22(01), 094-115 115 [122] Zand, A., J. Orwell, and E. Pfluegel. 2020. A secure framework for anti-money-laundering using machine learning and secret sharing. Paper read at 2020 International Conference on Cyber Security and Protection of Digital Services (Cyber Security), Dublin, Ireland. [123] Zhang, Y., and P. Trubey. 2019. Machine learning and sampling scheme: An empirical study of money laundering detection. Computational Economics 54 (3):1043–63.