This study examines the theoretical, structural, and empirical applications of Artificial Intelligence (AI) and Machine Learning (ML) architectures within the domain of regulatory compliance (RegTech) and supervisory technology (SupTech) for cross-border digital transactions. The exponential expansion of cross-border financial flows, real-time payment systems, and decentralized financial instruments has amplified regulatory fragmentation, multi-jurisdictional compliance friction, and sophisticated financial crime typologies. Utilizing institutional economics, information asymmetry theory, and computational compliance modeling, this paper analyzes how advanced algorithmic architectures—specifically Graph Neural Networks (GNNs), Natural Language Processing (NLP), and Federated Learning—optimize anti-money laundering (AML), counter-terrorist financing (CFT), and real-time sanctions screening. The findings demonstrate that shifting from legacy rule-based heuristics to adaptive, privacy-preserving AI frameworks significantly compresses false-positive rates, bridges cross-jurisdictional regulatory disparities, and establishes a dynamic, mathematically rigorous paradigm for global financial integrity.
Abstract The boundary between traditional organized crime and cybercrime is eroding. Long-established criminal groups increasingly rely on encrypted communications, darknet markets, and cryptocurrency-based money laundering, while profit-driven cybercriminal groups adopt the durable structures, division of labor, and governance mechanisms long associated with organized crime. This article examines this convergence, understood as the organizational, operational, financial, and technological integration of traditional criminal groups and cybercriminal networks. The study combines a qualitative analysis of documents published between 2020 and 2026, including law enforcement reports, court records, and assessments by international organizations, with a case study of the Hive ransomware group and its disruption in 2023, complemented by supporting cases such as Conti, Hydra Market, EncroChat, and the online fraud compounds of Southeast Asia. Three vectors of convergence are identified: ransomware-as-a-service models and inter-group alliances; darknet marketplaces and the wider crime-as-a-service economy; and direct alliances between hackers and conventional criminal groups, including trafficking-based forced criminality. The article develops an integrative framework that links each vector to the organizational features it produces, to established criminological theories, and to corresponding enforcement levers. It concludes that convergence is a profit- and opportunity-driven adaptation to a weakly guarded digital environment and that effective responses require synchronized pressure on offenders, finances, infrastructure, and criminal service providers.
Cybercrimes that exploit virtual assets—including laundering, concealment, and illicit financing through the dark web—are increasing rapidly, while existing tracking tools remain limited when offenders leverage multi-layer blockchain architectures and off-chain mechanisms to obscure fund flows. This paper proposes a practical full-node-based blockchain forensic framework for the automated detection and tracking of illicit virtual asset transactions across Layer-1 and Layer-2 environments. The framework operates a full-node network to construct a continuously updated database of all on-chain transactions, from which exchange-controlled internal addresses are identified using six formalized heuristics (H1–H6) expressed as a weighted-sum scoring model. A unified multi-layer transaction graph incorporates Layer-2 events—payment channel closures, rollup batch submissions, and bridge deposits and withdrawals—as contextual edge attributes correlated with Layer-1 settlement. Protocol-specific cross-layer correlation procedures, covering Arbitrum retryable tickets, Optimism cross-domain messages, zkSync Era batch commitments, and third-party bridge relays, were validated on live main-net transactions. Applying the framework to 7511 suspect wallet addresses, 821 (10.93%) were attributed to four Korean exchanges, and real laundering cases involving mixing and swapping—together with integrated real-time alerting and transaction-freeze request functions—demonstrate its direct applicability to law enforcement investigations. In addition, attribution reliability is quantified through the 98.80% labeling consistency observed across repeated independent collections of the same addresses, the standard forensic metrics are formally defined together with publicly released evaluation tooling, and the end-to-end detection latency is bounded analytically by the confirmation properties of the underlying protocols, substantiating the real-time capability of the framework.
Type of the article: Research ArticleAbstractThe blockchain financial system allows users to send money fast without any border restrictions. However, the same structure of the blockchain may be used as a means of laundering money. This paper assesses the relationship between the complexity of transaction networks and the likelihood of their illicit nature within the public Elliptic Bitcoin benchmark and examines whether anomaly detection using machine learning helps to interpret risks from an AML/CFT perspective. This empirical analysis assumes that Elliptic provides an anonymized transaction network in which nodes correspond to Bitcoin transactions, edges reflect directed transactions, and anonymized features facilitate licit/illicit classification of transactions. Furthermore, the dataset is not considered evidence of sender wallet addresses, receiver wallet addresses, transaction amount, timestamp, ownership of exchanges, user geography, and national AML/CFT effectiveness. Based on the labelled analytical dataset presented in the uploaded workbook (46,564 observations, including 42,019 licit transactions and 4,545 illicit transactions), a logit model found a significant positive correlation between illicit transactions and degree centrality (beta = 1.870, p < 0.001), clustering coefficient (beta = 0.940, p < 0.001), and flow entropy (beta = 0.680, p < 0.001). Isolation Forest and Autoencoder reached AUCs of 0.866 and 0.841, respectively. In turn, the coefficient measuring a country’s regulatory capacity and its interaction term are not included in the estimation because there is no country-window marginal effect. Therefore, this paper does not test for the impact of regulatory capacity of the USA, Singapore, and UAE on transaction classification.
Automated anti-money laundering (AML) on public blockchains is usually framed as a detection problem. Because the ledger is public and permanent, automated detection is feasible, but that record shows only that value moved, without showing who moved it or why. We review automated blockchain anti-money laundering as a system in which machine models and human analysts share each decision, following it through four stages: detection, attribution, adjudication, and reporting, and asking at each stage what automation does well, what it must leave to human judgment, and what goes wrong when that judgment is misplaced. The evidence shows a consistent asymmetry. Machine learning is strong at pattern-finding over the permanent public record, where models rank suspicion and clustering heuristics scale, but it weakens sharply as the task turns from finding a pattern to assigning meaning, identity, intent, or accountability. Drawing first on emerging AML-specific studies and then, where direct evidence remains insufficient, on human-factors research from adjacent high-stakes domains, we find an uneven evidence base. Automation is best supported for large-scale detection, alert prioritization, and parts of blockchain attribution, while the evidence becomes more limited as decisions require contextual interpretation, evidential judgment, accountability, and reporting. AML-specific studies identify explainability, flexibility, tool integration, supervisory justification, and human review as important operational requirements, but they do not yet establish how frequently analysts over-rely on, reject, or selectively follow automated recommendations. Evidence from aviation, healthcare, and public administration is therefore used to identify plausible failure mechanisms rather than to claim AML-specific effects. The result is an evidence-weighted allocation matrix that records, for each stage, the strength of the case for automation, the function retained by the analyst, the dominant failure mode, and the empirical question that remains unresolved. Support is strongest for detection, direct but context-dependent for attribution, and more provisional for adjudication and reporting.
This article presents a novel, first-of-its-kind predictive RegTech solution to address this challenge using machine learning methods. The rapid global adoption of Real‑Time Payment Systems (RTPS) has created a significant “velocity gap” in regulatory compliance. While expanding financial accessibility, these systems introduce new vulnerabilities into existing AML frameworks. Static, rule-based systems and batch processing architectures cannot effectively counter money laundering in sub-second transaction environments. This limitation enables sophisticated activities such as digital layering and smurfing that move illicit financial flows across networks faster than regulatory systems can react. The core of our solution involves the use of graph neural networks (GNNs). This approach enables real-time, pre-settlement risk assessment, preventing illicit transactions before execution. Unlike traditional AML systems that evaluate transactions in isolation, this framework analyzes the entire transaction network to detect coordinated illicit behavior in real time. GNNs capture complex structures such as loops, funnels, and bridges that indicate illicit activity. To support efficient implementation, the framework integrates Event-Driven Architecture (EDA). The proposed architecture introduces the concept of the Zero-Knowledge Proof (ZKP) protocol layer in order to make risk-sharing possible in a secure manner across multiple institutions. This allows the banks to cooperate with each other in order to combat financial crimes while maintaining their data sovereignty. With predictive graph analytics, event-driven integration, and private cooperation, the proposed architecture enables proactive compliance in real-time payment environments, including real-time payment systems such as FedNow, against high-speed financial crime.
One of these financial crimes, which seem to sound like a concept straight out of a dream until you get a sense of the magnitude of the issue, is money laundering. According to the United Nations, Between $800 billion and $2 trillion in illicit money is transacted through the world financial system each and every year. The problem with this approach is that the criminals seldom use only one bank. They thread their way across five, ten, and sometimes dozens of institutions, all seeing merely a harmless nugget. In isolation, looking at his or her own transaction logs, no single bank will easily know that there is a problem. This paper is about a system, called AMLNet, which tackles this blind spot. Unlike the traditional approach, which would allow banks to share their customers' data with each other,AMLNet trains a detection model on customers' data within each bank, and shares only what the detection model learned from the data, not the data itself. All collaborative training is documented in a blockchain ledger, making it transparent and tamper-proof. With a Zero-Knowledge Proof, each bank is able to prove cryptographically that it is acting honestly, but not disclose anything private. A graph of transaction data (accounts as nodes, transfers as edges) is used to extract structural features, which are compressed by PCA before being input to a Multi-Layer Perceptron (MLP) risk-scoring classifier of each account. Together they increase fraud recall by approximately 20% over any single institution operating alone, while maintaining a low false positive rate, and that the overall computation time is less than 10 minutes on an average laptop.
With the rapid advancement of decentralized finance (DeFi), security incidents related to cryptocurrency have become increasingly prevalent. After such incidents, attackers typically attempt to rapidly move stolen assets, concealing the origin of illicit funds and ultimately converting them into fiat currency. However, existing anti-money laundering (AML) methods struggle to cope with the semantic complexity of DeFi transactions. They either rely heavily on low-level token transfers, or perform protocol-agnostic money flow analysis, failing to capture the high-level intent of transactions. In this paper, we propose AMLGuard, a semantic-aware AML framework for account-based blockchains. AMLGuard tracks illicit fund flows from known malicious addresses by performing semantic analysis on complex DeFi transactions, enabling accurate and continuous laundering tracking. Given a complex transaction, AMLGuard combines static rule-based analysis with retrieval-augmented large language model (LLM) reasoning to infer implicit DeFi semantics, transforming raw transaction data into high-level semantic representations. Furthermore, for cross-chain transactions where laundering intent is not explicitly exposed, AMLGuard parses transaction parameters and performs argument parsing to recover cross-chain semantics, enabling seamless tracking across ledgers. Based on the inferred semantics, AMLGuard abstracts each transaction into a DeFi Semantic Unit (DSU). We evaluate the effectiveness of AMLGuard on 82 real-world laundering cases, involving illicit assets worth over $1 billion. Specifically, AMLGuard reconstructs compact illicit fund-flow topologies with destination precision of 94.4% and 87.6%, while achieving the highest address recall of 98.4% and 95.8% and destination recall of 94.1% and 93.8% on single-chain and cross-chain datasets.
The rapid expansion of U.S. financial technology platforms has created new vectors for money laundering, terrorist financing and financial crime that traditional anti-money laundering frameworks were not designed to address. This article presents a systematic literature review of 78 peer-reviewed studies published between 2015 and 2025 to examine the design, performance and policy implications of advanced anti-money laundering frameworks for U.S. fintech platforms. This study draws on evidence from financial criminology, regulatory law, computer science and organizational studies; the review finds that machine learning-based transaction monitoring systems reduce false positive alert rates by 40 to 70 percent compared to rule-based systems, as well as improving detection of sophisticated layering schemes. Blockchain analytics tools partially de-anonymize cryptocurrency transaction flows and have been used to identify illicit financial activity on major blockchain networks. Regulatory technology platforms automate suspicious activity reporting, beneficial ownership identification and customer due diligence workflows in ways that reduce compliance costs as well as improve regulatory data quality. However, the reviewed literature also documents persistent challenges, including algorithmic disparate impact in AML monitoring systems, beneficial ownership opacity through shell company structures, regulatory arbitrage between licensed exchanges and decentralized finance protocols and the systemic underutilization of suspicious activity report intelligence by law enforcement agencies. The article concludes with six evidence-based policy recommendations and a research agenda for advancing AML framework effectiveness in the rapidly evolving U.S. fintech sector. Keywords: Anti-Money Laundering, Fintech, AML Compliance, Machine Learning, Transaction Monitoring, Know Your Customer, Cryptocurrency Regulation, Regulatory Technology, Suspicious Activity Reporting, Financial Crime.
Abstract The same infrastructures that enable decentralised finance, NFT markets, and metaverse platforms also create new spaces for para‑crime. This article extends grey criminology to Web3 by applying three mechanisms of infrastructural illegality – parasitism, normative greyness, and platform co‑production – first developed for physical cross‑border grey economies (daigou). Drawing on technical and financial crime literature, we show how smart contracts, stablecoins, and DAO governance are parasitised for money laundering and fraud; how techno‑libertarian narratives of 'code is law' and decentralisation sustain normative greyness; and how algorithmic security and DAO co‑production reshape rather than eliminate para‑crime. The analysis reveals both structural parallels with physical grey economies and domain‑specific variations – most notably, the deeper internalisation of co‑production in code‑based systems. We argue that grey criminology must extend its infrastructural turn to virtual and metaversal spaces, and that enforcement paradoxes – where suppression threatens valued infrastructures – apply as much to blockchain protocols as to customs thresholds.
El presente artículo analiza la tensión estructural entre los marcos regulatorios de prevención del lavado de activos –Anti-Money Laundering (AML)– y la emergencia de las organizaciones autónomas descentralizadas –decentralized autonomous organizations (DAOs)–. A partir de una analogía con el relato La lotería de Babilonia, de Jorge Luis Borges, el texto examina cómo la arquitectura contemporánea de cumplimiento ha mutado en un sistema de azar burocrático que erosiona el principio de lesividad y abstrae excesivamente los bienes jurídicos en el derecho penal económico. Mediante un enfoque interdisciplinar que integra la teoría de juegos, la praxeología de la escuela austriaca y la dogmática penal garantista, el estudio sostiene que el régimen AML opera como una externalidad negativa y como un factor de exclusión financiera, especialmente en contextos de alta informalidad, como el colombiano. El análisis concluye que la gobernanza algorítmica de las DAO, fundamentada en la transparencia del código y en la responsabilidad individual directa, puede ofrecer un modelo alternativo de eficiencia para la integridad financiera. Frente a la capitis deminutio derivada de la intermediación centralizada, se propone la descentralización como un paradigma orientado a restituir la soberanía económica del individuo, sustituyendo la opacidad administrativa por la certeza de la lex cryptographica.
Abstract Purpose. This study examines how instant payment systems such as Brazil's PIX, public and permissioned blockchains, and central bank digital currencies (CBDCs) govern the trade-off among security, privacy, and regulatory compliance, including anti-money-laundering requirements. It consolidates the fragmented evidence into a single comparative instrument. Design and methodology. A systematic review compliant with PRISMA 2020 examined eighteen peer-reviewed studies on the three systems from 2014 to 2025. Studies were appraised and positioned within a Digital Payment Governance Framework, DPGF, whose three axes are the locus of control, the privacy spectrum, and the compliance architecture, each scored from 1 to 5, and interpreted against anti-money-laundering standards. Findings. PIX corresponds to a regulatory clarity model, with scores of 1 for locus of control, 4 for privacy spectrum, and 1 for compliance architecture. Public blockchains correspond to an autonomy model with scores of 5, 2, and 5. CBDCs and permissioned blockchains correspond to a hybrid governance model, with scores of 2, 2, and 2. Zero-knowledge proofs and homomorphic encryption are the most widely adopted techniques, and both face scalability and metadata limits. Hybrid architectures recur as the design preferred across the corpus. Originality. The DPGF supports comparing governance arrangements across centralized, decentralized, and hybrid architectures and identifies the security, privacy, and compliance balance of each. Selective disclosure embedded by design at the protocol level, supported by cross-system indicators, is the direction with the most support for next-generation payment governance.
Bitcoin (BTC) wealth distribution is often studied with macro indicators like wallet balances, prices, network activity, fees, and hashrate. This letter proposes a "Crypto-Microeconomic Observability Framework" to examine micro-level Bitcoin wealth disparities across five labeled agent classes: Service, Abuse, Malware, Individuals, and Benign. Using descriptive, inequality, and longitudinal concentration metrics, we show that Bitcoin wealth is highly concentrated across major classes, consistent with a persistent "Whale-Effect". Service entities hold the largest share of observed BTC (75.15%), while Abuse controls a disproportionately large share relative to its entity count (24.26% of BTC vs. 3.53% of entities). Individuals, Abuse, and Service show near-maximal within-class inequality (e.g., Gini = 0.9993 for Individuals), and time-series analysis indicates these patterns persist. Overall, Bitcoin wealth among labeled economic agents remains structurally uneven and concentrated in a small subset of entities.
Since the first implementation of a blockchain with Bitcoin in 2009, cryptoassets created and transacted using blockchain technologies have grown and diversified significantly. Because regulatory regimes, which govern cryptoassets, do not have global coverage, criminal actors find opportunities to commit cryptoasset fraud. While it can be difficult to distinguish between cryptoassets that are honest but high risk and cryptoassets that are outright fraudulent, investors seeking significant returns frequently invest in unregulated cryptoassets, namely cryptocurrencies and non-fungible tokens (NFTs). This study provides a crime script analysis to examine the chronological and functional steps offenders use to execute cryptoasset fraud. It considers three types of crypto asset fraud and how they have functioned over time: Ponzi schemes, cryptoasset exit scams, such as cryptocurrency “rug pulls,” and NFT “mint-and-run” schemes, where invested value is stolen from a crypto asset project. By outlining the fundamental crime script of cryptoasset fraud, this study considers the implications for regulators. Of note, this study shows that while the stages of cryptoasset frauds are consistent, the speed at which frauds are executed has, on average, increased significantly. This rapidity of execution provides enduring challenges to regulators, who often cannot respond quickly. This challenge must be considered if regulation is to be effective.
Terrorist financing is a major fuel for political violence and extremist operations in the world. The increasing advancement of digital technologies, cryptocurrencies, crowdfunding platforms, and social media has significantly transformed how extremist groups raise, transfer, and conceal funds, yet little has been done to examine the broader digital transformation of terrorist financing and its implications for the United States. This scoping review examined evolving trends, financing strategies, and operational challenges associated with terrorist financing networks and assessed their implications for the United States counterterrorism agenda. Following the Arksey and O’Malley guidelines for scoping reviews, relevant studies were identified through systematic database searches and screened using predefined inclusion and exclusion criteria. Ten studies were selected and analyzed thematically. The findings underscored four major themes: the digitalization of terrorist financing, the fusion of lawful and unlawful funding mediums, administrative and institutional weaknesses, and the growing need for collaborative and intelligence-driven disruption strategies. The review found that extremist financing increasingly operates within ordinary digital and financial ecosystems, making detection more difficult for regulators, financial institutions, and law enforcement agencies. The study concludes that terrorist financing has become more decentralized, adaptive, and technologically sophisticated than many existing counterterrorism frameworks are prepared to address. Hence, strengthening United States national security will require a more proactive digital financial monitoring, sophisticated regulatory systems, and stronger inter-sectoral collaborations to disrupt evolving extremist financing networks before they escalate into acts of violence.
Open access
2 source records
Terrorism, Counterterrorism, and Political Violence
Objective: This study examines the legal and procedural challenges posed by decentralised finance (DeFi) technologies to the anti-money laundering framework in Iraq, The research problem lies in the clear regulatory gap resulting from the decentralised nature of these platforms, which relies on smart contract technology and blockchain to eliminate the need for traditional financial intermediaries; this decentralised nature hinders the ability of Iraq’s Anti-Money Laundering and Counter-Terrorist Financing Law No. 39 of 2015 to control cryptocurrency flows and establish criminal liability in this context,، Method: The study adopted a comparative analytical approach, analysing the text of Iraqi legislation and comparing it with the operating mechanisms of decentralised finance platforms, whilst also examining the extent to which it complies with the updated international standards issued by the Financial Action Task Force (FATF) In particular, with regard to Recommendation No. 15, Results: the study reached a number of important conclusions, the most notable of which is that the current legal definitions of funds and financial institutions in Iraq are outdated, thereby limiting the ability of regulatory bodies to track virtual assets, Novelty: The study also identified procedural shortcomings in the handling of encrypted digital evidence and recommended urgent legislative reforms, including the regulation and oversight of Virtual Asset Service Providers (VASPs) through the establishment of a dedicated institutional framework.
Kabilesh C M, Dr. B. Raja, Dr. S. Geetha, Dr. V. Cyrilraj
As decentralized finance (DeFi) continues to scale, traditional forensic methodologies often fail due to their retrospective, "post-mortem" nature, analyzing illicit activities only after they are permanently recorded on the ledger. This project proposes coinEth, a real-time institutional blockchain surveillance and autonomous defense system designed for the Ethereum Sepolia network. The framework operates across a four-layer architecture: a Data Acquisition Layer that intercepts pending transactions via Alchemy WebSockets (WSS); a Persistence and Forensic Engine that utilizes SQLite and Python-based heuristics to detect suspicious behavioral patterns such as "structuring" and "high velocity"; a Governance Layer that executes an autonomous enforcement loop via a Solidity-based "Gatekeeper" smart contract; and a Visualization Layer built with Streamlit and PyVis. By assigning dynamic risk scores—categorized as Safe (Level 0), Warning (Level 1), and Frozen (Level 2)—the system can automatically broadcast on-chain transactions to freeze illicit accounts before fund exfiltration occurs. Furthermore, coinEth reconstructs a chronological "money trail" through sequential path mapping (T0 → T1 → T2...), ensuring a verifiable digital chain of custody for investigative reporting. This proactive approach shifts blockchain security from passive observation to active, real-time intervention, significantly enhancing the defense mechanisms available to institutional stakeholders.
Olha Kovalchuk, Ruslan Shevchuk, Serhiy Banakh, N. P. Holota · 6 authors
Abstract This study examines the relationships between national cryptocurrency regulation, anti-money laundering (AML) risks, and decentralized finance (DeFi) adoption across global jurisdictions. Using correspondence analysis, correlation techniques, and regression modeling with control variables, we analyze data from the Basel AML Index and Retail DeFi Rankings to identify structural patterns in the interaction between regulatory frameworks, institutional quality, and digital asset ecosystems. The results reveal a counterintuitive global distribution in which advanced economies with strong regulatory regimes and low AML risks tend to exhibit limited retail DeFi activity, whereas jurisdictions characterized by weaker institutions and higher money laundering risks show significantly higher levels of DeFi usage. Further, the correspondence analysis identifies three distinct clusters of countries defined by specific configurations of regulatory approaches, AML effectiveness, and DeFi adoption, indicating that these relationships are configurational rather than purely linear. Robustness checks demonstrate that qualitative features of regulatory regimes are more strongly associated with DeFi adoption than conventional quantitative indicators of economic development or governance quality, thereby distinguishing DeFi diffusion from broader cryptocurrency usage dynamics. Mediation analysis provides partial support for a compensatory pattern: financial inclusion is a significant negative predictor of DeFi adoption, though a statistically confirmed mediation pathway between AML risk and DeFi activity through financial exclusion was not established. The study also highlights substantial global regulatory fragmentation, with 57% of jurisdictions classified as “Undecided” or “Improving,” underscoring the ongoing difficulty of reconciling financial innovation with stability and risk mitigation. These findings provide evidence-based guidance for policymakers designing adaptive regulatory frameworks and establish a foundation for further research on the evolution of digital finance regulation.
By blurring the boundary between art and financial assets, non-fungible tokens (NFTs) have created regulatory ambiguity and criminogenic vulnerabilities in digital markets. The article applies the Howey Test to an original dataset of NFT-related cases that involve financial crime. As it turns out, functionally NFTs often resemble securities: they are characterized by information asymmetries, speculative dynamics, and weak oversight. These structural gaps make NFTs attractive to facilitate fraud, money laundering, wash trading, and nefarious exploitation on decentralized platforms and incidentally by way of traditional auction houses. NFTs highlight systemic limitations of analog regulatory frameworks to contain criminogenic risk posed by virtual assets. To enhance transparency, accountability, and consumer protection in evolving digital economies, the article concludes on a paradigm shift toward an adaptive, outcomes-based regulatory approach.
The increasing complexity of global financial systems has necessitated the adoption of more efficient and transparent mechanisms for combating money laundering (AML). Blockchain technology, with its decentralized, immutable, and transparent characteristics, presents a promising solution to address the limitations of traditional AML systems. This paper represents a review, exploring the potential applications of AI and blockchain in enhancing financial control systems, in particular, within AML compliance, focusing on key areas such as transaction monitoring, cross-institutional data sharing, and regulatory reporting. The integration of blockchain can streamline AML processes, reduce operational costs, and increase the effectiveness of detecting illicit financial activity. The combination of blockchain technologies and artificial intelligence algorithms in financial control is considered. It is shown how automation of transaction analysis can strengthen the stability of the banking system and prevent financial crimes. It is demonstrated that the convergence of Artificial Intelligence and blockchain technologies presents a transformative opportunity to strengthen AML frameworks, particularly in the face of rising crypto-enabled financial crimes. This research offers several important contributions to the academic literature. First, it presents a synthesis of the current status of artificial intelligence approaches used for compliance in detecting fraud in Bitcoin transactions. This review discusses the essential methodologies and tactics in a particular area that intersects finance and compliance but falls under the broader disciplines of AI-driven finance and decentralized finance (DeFi). The incorporation of AI into financial control marks a tremendous technological revolution that is affecting industries across the board. Second, the study assesses the current state of the publications, major trends, and research gaps, emphasizing areas that deserve additional investigation.
Considerando a crescente expansão do mercado de criptoativos e a recorrente associação do bitcoin a práticas de ocultação patrimonial, torna-se relevante examinar sua utilização no delito de lavagem de dinheiro, especialmente diante dos riscos de responsabilização penal indevida de agentes que atuam licitamente nesse setor. Objetiva-se analisar a utilização do bitcoin no delito de lavagem de dinheiro, a partir do exame de sua definição, de suas formas de circulação e de sua possível inserção em dinâmicas de ocultação e dissimulação de valores de origem ilícita. Para tanto, proceder-se-á a uma pesquisa de abordagem qualitativa, com emprego do método jurídico-dogmático e da linha crítico-metodológica, mediante revisão bibliográfica e documental da legislação e da doutrina especializada. Desse modo, observa-se que o bitcoin, embora apresente características que podem favorecer sua utilização em esquemas de lavagem de capitais, como pseudoanonimato, descentralização, mobilidade transnacional e inexistência física, não constitui, por si só, instrumento ilícito. O que permite concluir que sua relevância penal depende da demonstração concreta de vínculo com infração penal antecedente e da prática de atos voltados à ocultação ou dissimulação da origem ilícita dos valores.
Penelitian ini mengevaluasi efektivitas federated learning dalam mendeteksi alamat ilegal pada blockchain Ethereum untuk Anti Money Laundering (AML). Studi ini membandingkan XGBoost centralized dan federated dalam simulasi multi exchange, data dibagi secara horizontal menjadi 3 subset yang merepresentasikan entitas bursa independen. Untuk mengisolasi pengaruh pelatihan terdistribusi, pembagian data dilakukan secara homogen (IID), sehingga analisis difokuskan pada perbedaan mekanisme pembelajaran tanpa dipengaruhi heterogenitas data. Hasil menunjukkan bahwa model federated mencapai performa yang kompetitif dengan PR AUC 0,9962 dan akurasi 97,11%, dibandingkan model terpusat dengan PR AUC 0,9975 dan akurasi 97,75%. Namun, performa tersebut disertai peningkatan durasi pelatihan 4,01 detik dibandingkan 3,39 detik, yang disebabkan oleh beban komunikasi selama proses pembaruan model. Temuan ini menegaskan adanya trade off antara kinerja dan efisiensi dalam penerapan federated learning. Meskipun mampu mendekati performa pembelajaran centralized, pendekatan ini menimbulkan biaya operasional tambahan. Studi ini merupakan evaluasi dasar dalam kondisi terkontrol dan belum merepresentasikan skenario dunia nyata, sehingga diperlukan penelitian lanjutan pada data non IID dan skala sistem yang lebih besar.
Anti-Money Laundering regulatory frameworks share an unstated design premise: the adversary is human. We demonstrate that this premise is architecturally false: a fully autonomous, deterministic multi-agent system can perform every function of a human criminal organization without possessing computational mens rea. We formalize this system as HYDRA-A and prove that against it, intent-based AML detection mechanisms have zero expected utility. Contributions: (C1) A formal model of the autonomous AML adversary with role-by-role replacement of human criminal organization structure. (C2) The Theorem of Absent Mens Rea: a formal proof that a fully-specified autonomous adversary cannot possess criminal intent, derivable from the typed component interfaces of HYDRA-A. (C3) A Corollary of AML Framework Obsolescence: every intent-based detection mechanism has zero expected utility against HYDRA-A. (C4) A personality vector P=(rho, alpha, sigma, tau) with five adversarial archetypes. (C5) A No Stationary Nash Equilibrium theorem for the arms race between HYDRA-A and adaptive defenses. (C6) Zero-knowledge behavioral verification is the only architectural class that provides a formal defense guarantee against HYDRA-A.
Due to the fast development of cryptocurrency and blockchain technologies, the field of financial innovation, data privacy, and legal regulation has become a complex area with a multi-faceted regulatory environment. In this paper, the authors discuss the critical problem of ensuring the rights to privacy of individuals and the necessity of an effective control over the regulatory framework in decentralized digital financial systems. Although cryptocurrencies like Bitcoin have facilitated peer-to-peer payments, increased transparency, and financial inclusion, their pseudonymous and borderless characteristics have also brought serious concerns associated with money laundering, terrorist funding, market volatility, and consumer protection. In a comparative and interdisciplinary approach, the research assesses the current regulatory reactions and outlines the increasing role of international principles, constructed by the Financial Action Task Force. It contends that the conventional approaches to regulation, which were developed to deal with centralized financial institutions, cannot deal with the contingencies of decentralized ecosystems. In this regard, the paper will present a technology-based governance model that incorporates the use of law, institutional, and technological solutions to emerge with a harmonious regulatory strategy. This is highlighted in the study as the new technologies including blockchain analytics, artificial intelligence, smart contracts, and privacy protection tools like zero-knowledge proofs could be used to facilitate regulatory compliance without compromising user privacy. It also highlights the significance of risk-based, adaptive regulation, regulatory sandboxes and international collaboration in reducing regulatory arbitrage and global financial integrity. Finally, the paper argues that the future of cryptocurrencies regulation is in the creation of adaptable, innovation-oriented, and privacy-sensitive rules. A balance between law and technology can enable policymakers to create a secure, transparent, inclusive digital financial ecosystem and protect basic rights and the larger interest of society.