Abstract Smart contract vulnerabilities have caused billions of dollars in losses across decentralized finance. Finding reliable ways to detect such vulnerabilities has been a long-standing challenge for researchers. The growing capabilities of large language models (LLMs) are promising, but the factors that determine their reliability and capabilities remain poorly understood. This study investigates whether increasing inference-time computation using techniques like extended reasoning and structured prompting always improves vulnerability detection capability. It also identifies the most influential factors to select a model for this task. Using four prompting techniques, it evaluates 14 LLMs from seven families on 54 Solidity contracts. The experiment reveals a clear gap in detection capability across model classes. While six frontier models do not report false positives on verified-clean contracts, all three small open-source models report vulnerabilities in every case throughout the experiment. Moreover, a 11.5% drop in F1 score for one model was observed when increasing inference-time compute by enabling extended thinking. Also, prompting strategy has a limited effect on detection capability compared to model selection. The results challenge common assumptions and offer practical insights into the use of LLMs for smart contract vulnerability detection.
The rapid digitization of financial services has created increasingly complex environments in which financial institutions must process large volumes of heterogeneous transaction data while simultaneously protecting customers, detecting fraud, managing financial risks, and complying with regulatory requirements. Traditional centralized and rule-based fraud detection systems face significant challenges associated with data volume, processing latency, evolving fraudulent behaviors, class imbalance, and the increasing sophistication of cyber-enabled financial crimes. This paper proposes a distributed intelligent analytics framework for blockchain-based fraud detection and risk management in financial institutions. The framework integrates distributed big data analytics, artificial intelligence, machine learning, blockchain, graph-based learning, and intelligent decision support into a unified architecture. Distributed computing provides scalable processing of heterogeneous financial datasets, while artificial intelligence identifies anomalous transactions and predicts potential risks. Blockchain provides a complementary integrity, traceability, and verification layer for financial transactions. Graph Neural Networks can further model relationships among customers, accounts, devices, merchants, and transactions, enabling the detection of complex fraud patterns that may not be visible through transaction-level analysis. The framework builds on Ramareddy's work on distributed big data analytics for scalable knowledge discovery in heterogeneous systems and Chhunchha's investigation of blockchain's influence on financial institutions. Recent research also indicates growing interest in machine learning, graph-based models, federated learning, and blockchain for financial fraud detection. The proposed framework addresses important challenges including scalability, privacy, class imbalance, concept drift, explainability, cybersecurity, and regulatory compliance. The paper argues that combining distributed analytics with blockchain and AI can provide financial institutions with a more scalable, transparent, adaptive, and intelligent approach to fraud prevention and financial risk management.
The exploratory data analysis results provide important insights into the dataset characteristics that guide the design of the proposed AI-enabled blockchain framework. The class distribution graph shows a strong imbalance, with approximately 86.2% genuine samples and 13.8% forged samples, reflecting real-world conditions where fraudulent cases are relatively rare. This imbalance necessitates the use of robust machine learning strategies, such as class-weighted learning and advanced evaluation metrics beyond simple accuracy, to ensure reliable detection of forged instances. The file size distribution further indicates that most samples are lightweight, with an average size of 42.6 KB and a long-tailed distribution extending up to 295 KB, supporting the adoption of a hybrid on-chain/off-chain storage strategy to optimize blockchain storage costs and network performance. Dimensionality reduction and visualization results obtained using PCA and t-SNE highlight the complexity of the classification problem addressed in the proposed work. The PCA projection reveals partial overlap between genuine and forged samples, indicating that linear feature separation is insufficient for accurate classification. Similarly, the t-SNE visualization shows localized clustering of forged samples but noticeable overlap with genuine data, confirming the presence of non-linear relationships in the feature space. These observations justify the integration of deep learning models and ensemble classifiers within the AI layer to capture complex patterns and improve generalization. The image resolution distribution further demonstrates that most images fall within a consistent resolution range of approximately 300–700 pixels (width) and 200–550 pixels (height), ensuring stable model training while still requiring standardized preprocessing to handle resolution variability across training, validation, and test splits. Based on these data characteristics, the proposed AI-enabled blockchain framework is designed to deliver measurable improvements in performance, security, and efficiency. Experimental evaluation shows that the AI-driven valuation and classification modules achieve a fraud detection accuracy of 94.1%, with a precision of 91.6%, recall of 89.3%, and an F1-score of 90.4%, demonstrating reliable performance despite class imbalance. The blockchain layer achieves an average throughput of approximately 420 transactions per second with a confirmation latency of 2.6 seconds, while maintaining a low transaction cost of ₹18–₹25 per transaction through Layer-2 scaling and off-chain storage optimization. Smart contracts exhibit a 99.1% execution success rate and high vulnerability detection coverage during security analysis, validating the robustness of automated transaction execution. The expected outcomes of the proposed system include reduced transaction settlement time, enhanced fraud resistance, improved valuation transparency, and greater market accessibility through tokenization and fractional ownership. By combining AI-driven intelligence with blockchain-based trust and automation, the framework is expected to significantly reduce manual intervention, operational costs, and regulatory non-compliance risks in real estate transactions. Overall, the results and projections confirm that the proposed approach is well-suited for real-world deployment, offering a scalable, secure, and intelligent solution for next-generation real estate asset management systems.
In blockchain-enabled supply chain finance, traditional credit risk assessment models suffer from conflicts between data sharing and privacy protection, reliance on static evaluation methods, and limited data credibility. To overcome these challenges, this paper proposes a blockchain-based dynamic credit risk assessment model that integrates privacy computing and intelligent risk monitoring. First, blockchain’s immutability and traceability ensure the authenticity and transparency of supply chain transaction data, effectively mitigating information asymmetry and data tampering. Second, privacy-preserving technologies, including homomorphic encryption based on the Paillier algorithm and zk-SNARKs, enable secure data sharing and validity verification without exposing sensitive enterprise information, thereby improving assessment reliability. Third, a dynamic risk monitoring framework is constructed by combining smart contracts, long short-term memory (LSTM) networks, and an improved dynamic graph neural network (DGNN). LSTM models temporal risk evolution in transaction data, while DGNN captures risk propagation among upstream and downstream enterprises. Smart contracts synchronize transaction states in real time, allowing continuous updates of credit risk levels. The proposed secure information processing and dynamic graph modeling strategy also provides a valuable reference for trustworthy data interaction and intelligent decision-making in distributed electromagnetic sensing and communication networks, where reliable information propagation and adaptive resource management are essential. Experimental results based on a textile supply chain dataset show that the proposed model achieves approximately 94% credit assessment accuracy, outperforming traditional static models by 15%–20%, while maintaining excellent response speed and throughput for dynamic financial decision-making. The proposed framework provides a practical and secure solution for blockchain-based credit risk management and offers methodological insights for data-driven engineering systems requiring secure information fusion and dynamic network analysis.
The increasing demand for trustworthy and privacy-preserving credit reporting systems has exposed the limitations of both centralized and existing blockchain-based solutions, including scalability bottlenecks, weak privacy protection, and insufficient incentive mechanisms. To address these challenges, we propose LightCred, a novel consortium blockchain-based personal credit management framework that integrates lightweight nodes, Merkle proofs, multi-role smart contracts, and privacy-preserving cryptographic techniques. LightCred features a five-layer architecture that efficiently collects, verifies, stores, and serves credit data while ensuring data integrity, confidentiality, and regulatory compliance. Specifically, it (i) employs a low-cost and traceable data reduction mechanism through lightweight nodes and Merkle proofs to minimize storage and improve verifiability; (ii) introduces a multi-role smart contract model that enforces dynamic access control and fair incentive distribution based on participant reputations; and (iii) integrates zero-knowledge proofs and homomorphic encryption to support privacy-preserving credit scoring and querying. Experimental results demonstrate that LightCred achieves superior performance compared to five baseline methods, delivering up to 5% higher throughput, 3–5% lower privacy leakage, and 10–15% reduced storage costs, while maintaining competitive latency and auditability. These findings validate LightCred as a robust, scalable, and privacy-aware credit management solution, offering a viable alternative for modern credit reporting systems.
Financial institutions depend on trusted employees, contractors and service accounts, yet this trust creates an attack surface that conventional perimeter controls cannot observe adequately. This paper develops an Explainable Adaptive Hybrid Artificial Intelligence (EAHAI) framework for insider threat detection and for assessing whether security awareness training is reducing measurable insider-risk behaviour. The framework combines Isolation Forest filtering, bidirectional long short-term memory sequence modelling, Shapley Additive explanations, adaptive behavioural risk scoring and Zero Trust policy enforcement. A socio-technical assessment layer is added to link training inputs to observable outcomes, including knowledge gain, phishing susceptibility, policy-violation rates, reporting delay, behavioural-risk reduction and analyst-confirmed events. The paper defines the measurement scales, evaluation criteria, validation procedures and analytical techniques required for institutional replication. Because production banking telemetry and labelled insider incidents are rarely available for publication, the empirical component is presented as a transparent synthetic proof-of-concept based on CERT-style behavioural variables rather than as evidence from a real bank. In a deterministic simulation of 17,280 user-day records and 2,880 test windows, the proposed hybrid score achieved an F1-score of 0.944, ROC-AUC of 0.993 and false-alarm rate of 0.017, while producing interpretable feature attributions and training-effectiveness estimates. The study contributes a scalable, explainable and ethically governed design for insider-risk analytics, and identifies the conditions under which it should be validated before operational deployment. Keywords: insider threat detection; explainable artificial intelligence; adaptive risk scoring; security awareness training; Zero Trust; financial cybersecurity.
The rapid digitalization of financial services has transformed the global financial ecosystem, enabling faster transactions, enhanced customer experiences, and greater financial inclusion. However, this digital transformation has simultaneously increased the complexity, scale, and sophistication of financial fraud. Traditional rule-based fraud detection systems often struggle to identify evolving fraud patterns, resulting in delayed responses, increased false positives, and substantial financial losses. Artificial Intelligence (AI)-powered real-time fraud monitoring systems have emerged as a transformative solution capable of detecting suspicious activities instantly through advanced data analytics, machine learning, deep learning, natural language processing, and behavioral intelligence. These systems continuously analyze vast volumes of transactional and non-transactional data, enabling financial institutions to identify anomalies, predict fraudulent behavior, and automate risk management processes with unprecedented accuracy and speed. This literature review examines the evolution, applications, technological foundations, benefits, challenges, and future directions of AI-powered real-time fraud monitoring systems in modern financial services. The review highlights how AI enhances fraud detection capabilities across banking, payment systems, insurance, digital wallets, cryptocurrencies, and investment platforms while discussing critical concerns related to privacy, algorithmic bias, explainability, cybersecurity, and regulatory compliance. The findings demonstrate that AI-driven fraud monitoring represents a fundamental component of modern financial security infrastructure and will continue to shape the future of fraud prevention in increasingly digital financial environments.
The rapid advancement of digital technologies has significantly transformed auditing practices, leading to the emergence of audit analytics as an important research domain that integrates accounting, auditing, and data science. This study aims to examine the evolution, intellectual structure, influential contributions, and emerging research trends in audit analytics through a bibliometric analysis approach. Data were collected from the Scopus database using relevant keywords related to audit analytics and analyzed using VOSviewer to perform citation analysis, keyword co-occurrence analysis, density visualization, and collaboration network analysis. The findings indicate that audit analytics research has experienced substantial development, particularly with the increasing adoption of big data analytics, artificial intelligence, machine learning, predictive analytics, blockchain, and automation technologies. Citation analysis identifies key contributions focusing on the role of big data and artificial intelligence in improving audit quality, audit judgment, fraud detection, and decision-making processes. The keyword analysis reveals that recent research trends have shifted from traditional analytical methods toward intelligent and automated audit systems that support continuous auditing and risk-based decision-making. Furthermore, collaboration analysis demonstrates the global nature of audit analytics research, with the United States emerging as the most influential contributor and strong research connections among countries and institutions. This study contributes to the literature by providing a comprehensive understanding of the development trajectory of audit analytics and identifying future research opportunities related to generative artificial intelligence, explainable AI, cybersecurity, and digital audit transformation.
The increasing adoption of cryptocurrencies has created new opportunities for digital financial innovation while simultaneously exposing individuals and institutions to sophisticated forms of financial fraud. Conventional rule-based fraud detection systems have become inadequate in addressing the dynamic and complex nature of blockchain-enabled financial crimes, leading to growing interest in the application of artificial intelligence (AI). This study systematically reviews the literature on artificial intelligence techniques for cryptocurrency fraud detection, with particular emphasis on their relevance to the Kenyan digital financial ecosystem. The review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 framework. Peer-reviewed studies published between 2020 and 2026 were identified from Scopus, Web of Science, IEEE Xplore, ScienceDirect, SpringerLink, and Google Scholar. Following the screening and eligibility assessment, 19 studies were included in the final qualitative synthesis. The findings reveal that machine learning, deep learning, hybrid AI models, and blockchain analytics significantly enhance cryptocurrency fraud detection by improving anomaly detection, transaction monitoring, predictive accuracy, and anti-money laundering compliance. Compared with traditional rule-based approaches, AI techniques provide faster, more adaptive, and scalable solutions capable of detecting evolving fraud patterns in decentralized financial systems. However, the review also identifies challenges relating to limited high-quality datasets, algorithmic bias, lack of explainability, cybersecurity risks, privacy concerns, and inadequate regulatory frameworks, particularly within developing economies. Furthermore, the review highlights a scarcity of empirical research focusing on cryptocurrency fraud detection in Kenya and identifies opportunities for developing localized datasets, explainable AI models, and context-specific regulatory frameworks. The study concludes that artificial intelligence has considerable potential to strengthen cryptocurrency fraud detection and financial security in Kenya, provided that technological, ethical, and regulatory challenges are adequately addressed. The findings provide valuable insights for researchers, financial institutions, technology developers, and policymakers seeking to enhance AI-driven fraud prevention within the country's evolving digital financial ecosystem.
Blockchain and its killer applications, particularly decentralized finance (DeFi), are gaining widespread adoption, with over 5,200 DeFi projects deployed on mainstream blockchains as of January 2026. At the same time, security risks in DeFi are becoming increasingly serious. However, existing DeFi detection tools usually cover only specific attack types, exhibiting severely limited detection coverage. In this paper, we argue that an effective way to address this gap is to pre-screen vulnerable instances from large volumes of smart contract functions and call sequences. This is motivated by a key phenomenon we term "perilous temporal asymmetry". Inspired by this, we propose DeFiScreener, the first automated pre-screening framework for DeFi attacks that uses historical exploit cases to identify potentially vulnerable functions and call sequences. Given the full source code of a target project, DeFiScreener builds Function Call Trees (FCTs) and generates semantic embeddings for each function using a large language model (LLM), allowing both program structure and function intent to be analyzed together. It then applies a dual-level screening process. At the function level, function embeddings are matched against an Attack Pattern Library of historically exploited functions. At the sequence level, the proposed Attack Pattern Oriented Monte Carlo Tree Search (APO-MCTS) efficiently explores the FCTs and screens vulnerable call sequences. The identified candidates are ultimately passed to an LLM for further interpretive and security analysis. We empirically evaluate the DeFiScreener over datasets comprising 207 real-world DeFi attack incidents. Experimental results demonstrate that DeFiScreener achieves a remarkable 98.55% recall and 84.30% precision in attack pre-screening.
ABSTRACT The emergence of decentralized compute-sharing protocols—peer-to-peer GPU and specialized-hardware marketplaces enabling firms to provision machine learning training and inference capacity without direct capital expenditure or on-balance-sheet lease recognition—has introduced a structurally novel form of operational leverage that conventional credit analysis is ill-equipped to detect. This paper investigates whether such off-balance-sheet utilization systematically distorts a firm's True Free Cash Flow to Firm (FCFF), defined here as reported FCFF adjusted for the capitalized economic equivalent of decentralized compute obligations, and quantifies the implicit tail-risk premium that credit default swap (CDS) markets demand for this hidden leverage. We formalize the problem in three stages. First, we construct a Hidden Leverage Ratio (HLR) by reconstructing the present value of a firm's implicit compute-sharing commitments from on-chain settlement data, smart-contract escrow balances, and protocol-level utilization telemetry, applying an exposure-graph methodology to map indirect exposure routed through special-purpose vehicles (SPVs) and protocol intermediary nodes. Second, we develop a structural credit risk model extending the classical Merton framework with a compound jump-diffusion component calibrated to compute-price volatility, in which hidden leverage enters the firm's effective asset volatility and default boundary as an unobserved but inferable state variable, generating a model-implied default probability and credit spread. Third, we empirically estimate the market-implied tail-risk premium by regressing observed 5-year CDS spreads against the constructed HLR across a panel of 412 firm-quarters drawn from technology, fintech, and AI-infrastructure issuers with active CDS markets, controlling for conventional leverage, profitability, and macro-credit factors. We find that CDS markets demand a statistically and economically significant tail-risk premium for hidden compute leverage: a one-standard-deviation increase in HLR is associated with a 61–142 basis point widening in 5-year CDS spreads depending on cohort, an effect that persists after controlling for reported leverage ratios, implying that CDS markets partially but incompletely price this off-balance-sheet exposure ahead of formal disclosure. The structural model achieves an R² of 0.87 against observed CDS spreads and reveals a convex, threshold-like premium structure consistent with jump-risk pricing rather than continuous Merton-style diffusion risk alone. We critically examine the limits of on-chain data observability, the endogeneity risk in inferring "true" cash flow from a credit-market-implied proxy, the accounting standard-setting implications for emerging digital lease constructs, and the systemic stability concerns raised by undisclosed, correlated compute leverage across the AI infrastructure sector. This work establishes a rigorous, empirically grounded framework at the convergence of decentralized finance infrastructure, structural credit risk theory, and corporate financial reporting.
As the blockchain technology and decentralized finance have grown rapidly, the number of fraudulent and anomalous activities has risen.The paper suggests a detectable graphbased anomaly detection system to detect suspicious Ethereum transactions.One 10,000 Ethereum transactions dataset was gathered through the Etherscan API within a 14 hour observation period and a directed transaction graph was created out of that dataset, where 14 behavioral node features were engineered.Three graph neural network (GNN) models, namely, Graph Convolutional Network (GCN), Graph Attention Network (GAT), and GraphSAGE, were checked on 5-fold cross-validation, and compared to three standard baseline classifiers, which are Logistic Regression, Random Forest, and XGBoost.GraphSAGE had the highest overall accuracy of 82.32, F1-score of 0.6389, and ROC-AUC of 0.8202, and GCN and GAT had near-zero recall on the minority class.XGBoost was the best baseline with the highest accuracy (94.41) but with significantly lower recall (0.2766) and F1-score (0.3801) compared to GraphSAGE, which is indicative of graph-based models being more balanced in precision and recall in detecting anomalies with class imbalance.The Local Interpretable Model-agnostic Explanations (LIME) showed outgoing transaction value features and account balance to be most important predictors of anomalous behavior.The results establish the promise of using GNNs in conjunction with explainable AI to secure blockchains, as well as reveal the challenges such as the class imbalance and ground-truth verified labels.
The rapid expansion of decentralized finance has introduced unprecedented systemic risks, most notably the phenomenon of stablecoin runs. Traditional econometric models analyzing financial fragility rely heavily on retrospective data, which is insufficient for tracking high-velocity, algorithmic bank runs on blockchain networks. This paper proposes a cloud-native architectural solution utilizing distributed Amazon Web Services middleware to ingest, normalize, and analyze blockchain ledger data in real-time. By deploying an asynchronous Python orchestration pipeline integrated with eXtreme Gradient Boosting and K-Nearest Neighbors algorithms, the proposed system identifies transaction velocity anomalies indicative of panic-selling and de-pegging events. This methodology fundamentally shifts the analysis of stablecoin fragility from theoretical post-mortem to programmatic, real-time detection. Preliminary architectural evaluations demonstrate that decoupling the data ingestion layer from the predictive inference engine significantly reduces latency, providing financial regulators and researchers with a scalable, deterministic tool for monitoring digital asset stability.
The rapid evolution of financial technology has transformed the global financial landscape, creating opportunities for innovation, inclusion, and efficiency while introducing systemic risks, regulatory uncertainties, and challenges to financial stability. This study presents a bibliometric review of global research trends at the intersection of financial technology and financial stability from 2000 to 2025, mapping the intellectual structure, identifying emerging themes, and highlighting influential contributions. Using Scopus data, the analysis examines 339 peer-reviewed documents across 242 sources. Bibliometric techniques were applied through VOSviewer, Bibliometrix (R), and Biblioshiny to evaluate publication trends, influential authors, thematic clusters, co-authorship networks, and keyword co-occurrences. The results show an average annual growth rate of 21.46 percent, with a marked increase in publications after 2017 coinciding with the mainstream adoption of digital finance and heightened policy focus on financial resilience. Findings indicate that financial technology promotes financial inclusion, banking efficiency, and economic empowerment, yet also introduces cybersecurity threats, regulatory gaps, and systemic vulnerabilities, particularly in emerging markets. Dominant themes include blockchain, digital payments, financial literacy, and central bank digital currencies, with decentralized finance and artificial intelligence emerging as fast-growing areas of scholarly interest. Geographically, China leads in publication volume, while the United Kingdom and the United States dominate in scholarly influence. This review provides a strategic roadmap for researchers and policymakers to navigate the evolving financial technology landscape and emphasizes the need for future research to integrate ethical governance, artificial intelligence risk management, and inclusive financial innovation frameworks.
Sai Srikanth Madugula, Peplluis Esteva De La Rosa, Daya Shankar
Decentralized Finance (DeFi) lending protocols currently rely on heuristic, utilization-based bonding curves that mandate severe over-collateralization, systematically excluding under-collateralized assets like corporate invoices. This paper introduces a mathematically optimal pricing mechanism for decentralized credit: the Reverse Kelly Automated Market Maker (rkAMM), the core engine of our proposed lending framework. By inverting the Kelly Criterion, traditionally used for optimal bet sizing, we construct a dynamic interest rate discovery protocol that explicitly prices individual loan risk. The rkAMM ingests real-time Probability of Default (PD) streams from an off-chain Explainable AI oracle and dynamically calculates the exact interest rate required to sustain target liquidity provider (LP) yields. We mathematically derive the Reverse Kelly pricing function ($r = \frac{y + PD}{1 - PD}$), proving its strictly convex superiority over Aave and Compound's static utilization curves in managing capital efficiency. Furthermore, we deploy the rkAMM architecture via Solidity smart contracts, optimizing for gas-efficient 1e18 (WAD) floating-point arithmetic. To ensure decentralized transparency, our simulation infrastructure leverages MLflow for tracking yield hyperparameters, Data Version Control (DVC) linked to DagsHub for versioning Real-World Asset (RWA) data arrays, and localized edge-inference via Ollama (Llama-3) and Hugging Face (FinBERT) for zero-cost predictive modeling. Monte Carlo simulations across 10,000 macroeconomic stress scenarios confirm that the rkAMM maintains protocol solvency and stabilizes LP yields at 12-15\% net of expected credit losses. This work provides the foundational financial engineering required to bridge the \$2 trillion global supply chain finance gap using permissionless blockchain infrastructure.
Hai Liang, Xiaoye Lu, Changsong Yang, Yujue Wang · 6 authors
Smart contracts are immutable programs that automatically execute predefined logic. Once deployed, their underlying vulnerabilities are notoriously difficult to patch and highly susceptible to malicious exploitation, often leading to severe financial losses. Although existing vulnerability detection methods have demonstrated certain advantages, they still fail to achieve adequate structural–semantic coverage of vulnerability-relevant behaviors, as they are unable to jointly model opcode semantics, control-flow transitions, and data-dependency relations. To overcome these limitations, this paper proposes a novel smart contract vulnerability detection model named Cross-aligned Penetrative Graph Network (CPGNet). Specifically, CPGNet first constructs control flow graphs and data flow graphs from the abstract syntax tree, and combines them with opcode semantic embeddings to form a multidimensional initial code representation. Based on this representation, a cross-alignment mechanism is introduced to effectively capture and integrate the complex interactions between control-flow transitions and data-flow dependencies. Furthermore, an explicit–implicit feature penetration architecture is designed to inject shallow local opcode patterns into the deep semantic modeling process, enabling multi-source features to dynamically complement each other. By jointly modeling opcode semantics, control-flow structures, and data-dependency relations, CPGNet significantly enhances the representation capability for hidden and complex vulnerability patterns. Experimental results on two datasets show that CPGNet achieves stable performance, with F1-scores of 88.69% and 90.58% on the benchmark Ethereum dataset, and 78.10% and 71.53% on DIVE for reentrancy and timestamp dependency detection, respectively. These results verify the effectiveness of jointly modeling opcode semantics and graph-level structural dependencies.
The growth of the usage of decentralized applications on Ethereum has seen the rise of an increasing number of bad actors that are using it to commit fraud, phishing, money laundering and financial scams. Traditional detection methods are less effective to detect accounts with more complex and changing behaviours. The paper suggests a novel multi-level framework for detecting malicious Ethereum accounts based on supervised classification and adaptive anomalous account verification using a routing based on probabilities. To get the transaction behavior features, opcode features and time-interval features from the publicly available EtherShield data set, we use the entire data set to extract the entire features. The first is a Level-1 where an XGBoost machine learning model classifies Ethereum accounts into Fair, Likely Malicious and Malicious categories, and outputs calibrated probability scores for any account. Uncertainty about malicious accounts are escalated to level-2 where anomaly verification and behavioural re-assessment are carried out by using models such as Random Forest and Isolation Forest. The final classification is obtained by decision fusion process, which combines the results obtained from both levels. The Random Forest-based verification module is evaluated in the experiments and is found to be 95% accurate, 94% macro precision, 95% macro recall and 95% macro F1-score, which is significantly better than the Isolation Forest (baseline). Besides, stratified 5-Fold Cross Validation further demonstrates that the proposed framework is robust and generalizable with a mean accuracy of 94.96% ± 0.43, mean precision of 94.40% ± 0.42, mean recall of 94.84% ± 0.47 and mean F1-Score of 94.66% ± 0.42. The proposed framework proves to be an effective solution to minimize misclassification, enhance the reliability of detection and offer a scalable answer to safeguard Ethereum blockchain ecosystems from newly emerged malicious activities.
Introduction. Modern information technologies form an interconnected ecosystem of financial management. The practical significance lies in the development of an algorithm for overcoming personnel, integration and cyber risks. The development prospects are related to the convergence of predictive analytics, explicable artificial intelligence, and distributed ledgers. Materials and Methods. The research is based on scientific publications, business media and corporate reports. The case study method was applied using methods of systematization and comparative analysis based on the material of five major domestic companies (Sberbank, X5 Group, Lukoil, Magnit, Alfa-Bank). Results. The main technological solutions (enterprise resource planning systems, cloud platforms, artificial intelligence, big data, distributed registries) are systematized, their functional purpose and barriers to integration are determined. The evolution of digitalization has been confirmed: from automation of operations to the intellectualization of analysis. The effects were recorded: reducing transaction operating costs by up to 27 %, reducing fraudulent transactions by 92 %, optimizing inventory, and issuing digital financial assets worth over 600 billion rubles. Conclusion. Modern information technologies form an interconnected ecosystem of financial management. The practical significance lies in the development of an algorithm for overcoming personnel, integration and cyber risks. The development prospects are related to the convergence of predictive analytics, explicable artificial intelligence, and distributed ledgers.
Open access
Digitalization and Economic Development in Agriculture
Decentralized Finance (DeFi) has revolutionized financial services by eliminating traditional intermediaries, but this openness creates new vulnerabilities that malicious actors exploit for fraud. The pseudonymous nature of blockchain transactions and lack of centralized oversight make traditional fraud detection methods inadequate for the DeFi ecosystem. This paper introduces ChainGuard, an end-to-end fraud detection system that leverages verifiable machine learning with zero-knowledge Succinct Non-Interactive Arguments of Knowledge (zk-SNARKs). ChainGuard utilizes a comprehensive approach that combines advanced feature extraction from Ethereum blockchain transaction data, optimized machine learning models, and on-chain verification through zk-SNARKs. Our solution enables privacy-preserving fraud detection while maintaining the ability to verify results without exposing sensitive transaction data and the internal architecture of the model. We demonstrate that ChainGuard achieves permissible accuracy in detecting fraudulent activities across Ethereum and various DeFi platforms while ensuring computational efficiency through multiple optimization techniques, including quantization. Experimental results show that our approach achieves performance comparable to traditional fraud detection methods while maintaining the decentralized and trustless nature of blockchain systems.
Sabri Hisham, Mokhairi Makhtar, Azwa Abdul Aziz, Ahmad Firdaus · 6 authors
Abstract The global expansion of blockchain technology has unfortunately been accompanied by a rise in fraudulent activities within decentralized applications (DApps), leading to substantial financial losses. The immense volume of transaction data (big data) makes manual detection of abnormal account behavior impossible, necessitating the use of automated machine learning (ML) techniques. Existing anomaly machine learning detection approaches often rely on single-classifier models that suffer from limited generalization, high false-positive rates, or insufficient feature relevance, thereby compromising detection accuracy and system security. Moreover, the high dimensionality and complexity of blockchain data necessitate more sophisticated and robust methodologies that can effectively identify relevant features and leverage the strengths of multiple learning algorithms. This study addresses a key gap by proposing a novel anomaly detection framework for the Ethereum blockchain that distinctively integrates the Boruta feature selection algorithm with a combination of ensemble methods and a fuzzy logic classifier. Specifically, we investigate the performance of various ensemble techniques (bagging, boosting, voting, and stacking) combined with foundational models (Decision Tree, Random Forest, K-Nearest Neighbors, and XGBoost), including a specialized Fuzzy ENORA model. The objective is to significantly enhance the accuracy of anomaly detection. Our results demonstrate that the ensemble models consistently and significantly outperformed single-classifier models, achieving a mean performance metric of 0.99 across accuracy, precision, recall, and F1 score, affirming the robustness of the proposed Boruta-driven ensemble approach for securing blockchain transactions.
Ethereum account classification is essential for identifying individuals engaged in illicit transactions and analyzing behavioral patterns across various account types. This process serves as a critical mechanism for monitoring and regulating unlawful activities within transactional markets. However, the Ethereum network exhibits the characteristics of a complex heterophilic graph which poses significant challenges to the effectiveness and performance of conventional graph neural networks (GNNs). To address this challenge, the present study proposes FSGCN(Fourier-Sage GCN), a novel architecture for heterophilic graph neural networks (GNNs) that integrates Kolmogorov–Arnold Networks (KANs) with GraphSAGE. FSGCN is specifically designed to adapt efficiently to the structural complexity of heterophilic graphs. By leveraging KANs to extract high-order neighborhood information and employing GraphSAGE to capture low-order neighborhood patterns, FSGCN effectively aggregates both homophilic and heterophilic features, thereby improving classification performance. Furthermore, to improve training efficiency and generalization, we propose the MLPInit weight initialization scheme and the DropEdge graph augmentation technique. Experiments on a large-scale Ethereum transaction dataset show that FSGCN achieves an F1-score of 91.8% and a classification accuracy of 91.6%, significantly outperforming traditional homophilic and heterophilic GNN baselines. Additionally, FSGCN demonstrates high training efficiency, completing each epoch in just 2.302 s per epoch and improving overall training speed by 130.4% compared to conventional GraphSAGE.
KENOS — Kohenoor Operating System Official Description and Public Disclosure KENOS, the Kohenoor Operating System, is the unified digital operating environment of the Kohenoor ecosystem. It brings together artificial intelligence, Education 3.0, blockchain infrastructure, hybrid finance, business applications, development tools, governance controls and operational supervision within one coordinated ecosystem. <Explainer film added> The transition from KENHYFI Hub to the broader KENOS architecture reflects the continued expansion of the Kohenoor ecosystem. KENHYFI was originally developed as a hybrid-finance and ecosystem hub. However, the name and positioning of KENHYFI did not fully represent the wider capabilities that had developed around it, particularly: KAI — Kohenoor Artificial Intelligence, the ecosystem’s multilayered intelligence powerhouse and orchestration system. ProEdge, the Education 3.0, professional learning and workforce-development hub. Blockchain, development, commerce, security, governance and institutional-support applications extending beyond hybrid finance. For this reason, KENOS was established as the umbrella operating environment for the complete ecosystem. KENHYFI remains an important integrated hub within KENOS, but it no longer represents the entire ecosystem by itself. The relationship is therefore defined as follows: KENOS is the complete Kohenoor Operating System and umbrella ecosystem. KAI is the principal intelligence and orchestration powerhouse of KENOS. ProEdge is the principal Education 3.0 and professional-learning hub. KENHYFI is the integrated hybrid-finance and ecosystem-services hub within KENOS. Other applications and modules provide specialized capabilities in blockchain, commerce, development, security, finance and operational management. KENOS is built on three foundational pillars: Education 3.0 Artificial Intelligence Blockchain These pillars support the complete digital-economic journey: Learn → Plan → Build → Execute → Analyze → Supervise → Improve → Scale Artificial Intelligence Pillar KAI, Kohenoor Artificial Intelligence, serves as the principal intelligence powerhouse of KENOS. KAI is designed as a multilayered hybrid-intelligence and workflow-orchestration system rather than a conventional chatbot. It supports knowledge retrieval, document analysis, specialist-role activation, business intelligence, financial analysis, educational guidance, application planning, risk assessment, reporting, workflow coordination and Human-in-the-Loop escalation. Within KENOS, KAI connects users, knowledge, applications, workflows and authorized human decision-makers. Education 3.0 Pillar ProEdge serves as the principal learning and professional-development hub within KENOS. It supports practical education, workforce transformation, professional training, institutional capacity building and industry-linked learning in areas including: Artificial intelligence Blockchain and Web3 Business intelligence Cybersecurity Hybrid finance Digital transformation Communication and professional skills Software and application development Entrepreneurship and business execution ProEdge ensures that KENOS is not limited to providing technology. It also develops the human capability required to understand, manage and apply that technology effectively. Blockchain Pillar The blockchain pillar provides smart contracts, programmable assets, digital ownership, transparent records, settlement mechanisms, token utilities and verifiable ecosystem operations. Blockchain functions are designed to operate alongside KAI-supported intelligence, business rules, governance controls and authorized human supervision. Purpose of KENOS KENOS is designed to support individuals, professionals, businesses, educational institutions, developers, government entities and other organizations participating in the AI-powered digital economy. It connects learning with intelligence, intelligence with execution and execution with monitoring and supervision. KENOS may support: Education and professional development Artificial intelligence and business intelligence Financial and hybrid-finance services Blockchain and smart-contract development Digital commerce and procurement Application and software development Security and operational resilience Governance and institutional intelligence Reporting, monitoring and supervision Development Status At the time of this publication: KENOS is in the Early Beta phase. KENHYFI Hub is in the Alpha+ phase. Individual applications and modules may have different levels of development, testing and availability. The official public web host and disclosure gateway for KENOS is: https://www.kohenoor.net Within the KENOS architecture: KAI serves as the principal intelligence and orchestration layer. KENHYFI Hub operates as an integrated hybrid-finance and ecosystem services hub. Education 3.0 platforms support learning, reskilling and professional development. Blockchain applications provide smart-contract, digital-asset, settlement and verification capabilities. Business and development modules support planning, commerce, procurement, software development, financial intelligence, security, reporting and operational management. KENOS is intended to serve individuals, professionals, businesses, educational institutions, developers, government organizations and other entities participating in the AI-powered digital economy. The architecture is modular and may support public web access, controlled organizational deployments, private-cloud environments, local installations, sovereign infrastructure and integration with existing enterprise systems. Governance remains a core element of KENOS. High-stakes activities are intended to remain subject to authorized human review, role-based permissions, validation controls, risk classification, activity logging and Human-in-the-Loop approval. At the time of this publication, KENOS is in the Early Beta phase, while KENHYFI Hub is in the Alpha+ phase. Applications and modules within the ecosystem may therefore have different levels of development, testing, availability and production readiness. The official public web host and disclosure gateway for KENOS is: https://www.kohenoor.net This publication provides the official conceptual definition, ecosystem positioning, service scope, architectural relationships, development status, governance principles and public-disclosure framework of KENOS. Keywords: KENOS; Kohenoor Operating System; Kohenoor Technologies; KAI; Kohenoor Artificial Intelligence; KENHYFI; Education 3.0; artificial intelligence; blockchain; hybrid finance; digital economy; business intelligence; digital transformation; smart contracts; Human-in-the-Loop; ecosystem architecture; AI governance; Web3; enterprise AI; institutional intelligence Kohenoor Technologies remains committed to transparency, security, responsible disclosure, and continuous improvement of the KEN ecosystem. #kenhyfi #kai #hyfi #kohenoortechnologies #futureofeducation #futureoffinance #futureofai #kohenoorken #cryptocurrencies #kohenoorken #AI #actionai #agenticai #AGI #ArtificialGeneralIntelligenceAGI #AIAssistant #education3 #defi #hybridfinance #hyfi #cedefi #blockchain #innovation #settlements #auditreadycertificates #DASC #cybersecurity #web3 #businessintelligence #proedge #industrygradetrainings #quantumcomputing
Decentralized finance exposes supervisors to fast-moving, networked credit risks. General-purpose LLM agents fit this setting poorly: they over-read weak evidence and recommend high-stakes interventions, while existing evaluations offer no regulator-aligned way to measure the resulting false alarms. We introduce DeXposure-Claw, a forecast-grounded agentic supervision system that routes LLM decisions through structured evidence: (1) DeXposure-FM, a graph time-series foundation model, forecasts future exposure networks; (2) deterministic monitors and stress scenarios then turn those forecasts into typed alerts, attribution signals, and scenario evidence; and (3) data-health and confidence gates constrain escalation before DeXposure-Claw emits auditable supervisory tickets with rationales. We further develop DeXposure-Bench, a six-axis evaluation harness, whose decision axis scores tickets against a regulator-aligned absolute-loss ground truth and an explicit false-intervention rate. Experiments on five years of weekly real data fully support our system. Code is at https://github.com/EVIEHub/DeXposure-Claw.
With the rapid development of digital finance, the mode of enterprise credit risk assessment has changed, and now also requires methods that can handle large-scale, diverse data and smart computation. The old system of credit rating has been based on the results of past financial reports and is no longer suitable for evaluating the changes and risks in modern corporate finance. This paper proposes a multi-dimensional model for mining credit reports of mining enterprises and combines structured financial data, transaction information, operating indicators, and other unstructured auxiliary data such as social media presence, online communication, supply chain dynamics, etc. By building a relatively detailed credit report, the bank can gain some information on the risk of a company's credit and its repayment ability for a loan. Algorithms that use machine learning, deep learning, ensemble models and predictive analysis are also known as intelligent default risk assessment algorithms that enhance the accuracy and flexibility of credit assessment. The following are ways to discover abnormal or complex patterns in a large amount of data early on for risk early warning, online credit assessment and dynamic portfolio management. Interoperability of digital finance platforms can support lifelong learning, automation and scalable high-frequency financial data, and maintain security, privacy and regulatory compliance. Although the above have been achieved, there are still deficiencies in the quality of data, interpretability of models, adherence to regulations, and sufficient computational resources, especially for small and medium-sized enterprises and new market institutions. Future research directions include building explainable AI systems, continuous learning, integrating multiple types of data (multimodality), and decentralized finance (DeFi) based on blockchains. At this point, the above technologies are expected to help enterprises strengthen credit risk management in the age of digital finance and provide more accurate and timely credit evaluations.