Jishnu Patlola, Rishitha Manyam, Himakar Chappidi, K Suvarchala
This paper investigates the application of CodeBERT, a pre-trained transformer model, to improve the detection of vulnerabilities in smart contracts.Smart contracts, while central to blockchain technology, are susceptible to security flaws that can result in significant financial and operational risks.By fine-tuning CodeBERT on labeled datasets specifically curated for smart contracts, our approach enhances the precision and efficiency of identifying various security issues.This method not only offers a robust solution to the existing challenges in blockchain security but also contributes to the broader efforts to secure decentralized systems and ensure the reliability of blockchain applications
This study explores the optimized application of combining blockchain (Blockchain) and artificial intelligence (AI) in the intelligent risk control of decentralized finance (DeFi). Although the decentralization and transparency of DeFi have driven financial innovation, they have also introduced risks related to market manipulation, smart contract vulnerabilities, and liquidity. Traditional centralized risk control approaches struggle to adapt. This research proposes a blockchain+AI-based intelligent risk control framework. Blockchain’s tamper-resistance enhances transaction security, while AI’s intelligent learning capabilities improve risk identification. Experimental results show that this model outperforms traditional solutions in detection accuracy (94.1%), false alarm rate (2.1%), and detection latency (180ms), and it remains robust under high market volatility. The findings suggest that combining blockchain and AI can effectively strengthen DeFi risk control, enhance system transparency and security, and provide theoretical and practical directions for future intelligent and automated risk management.
Jonas Gabriel Borges da Silva, Diógenes José Gusmão Coutinho
O presente trabalho abordou o potencial dos smart contracts como ferramentas para a redução da burocracia, explorando simultaneamente os desafios jurídicos e as considerações cruciais para sua implementação efetiva no Brasil. Inicialmente, destacou-se a capacidade dos smart contracts de automatizar a execução contratual, minimizar a necessidade de intervenção humana e eliminar intermediário, o que poderia simplificar processos e diminuir entraves burocráticos. A transparência proporcionada pelas plataformas blockchain também foi apontada como um fator que contribui para a construção de confiança. No entanto, a implementação generalizada dos smart contracts enfrenta desafios jurídicos significativos. A principal barreira identificada é a ausência de legislação específica no Brasil para regular esses contratos, gerando incertezas sobre sua validade e eficácia. A interpretação da vontade das partes expressa em código, a definição da natureza jurídica dos smart contracts e as questões de jurisdição e lei aplicável em transações descentralizadas foram também levantadas como complexidades a serem resolvidas. Ademais, foram consideradas as implicações práticas da implementação, incluindo a segurança do código, a interoperabilidade entre plataformas e a necessidade de proteção dos direitos dos contratantes em um ambiente de execução automática. A adoção de mecanismos como a regulação dinâmica e os sandboxes regulatórios foi sugerida como uma possível abordagem para acompanhar a evolução tecnológica e criar um ambiente jurídico mais adaptável. Em suma, embora os smart contracts ofereçam um potencial considerável para simplificar processos e reduzir a burocracia, sua adoção bem-sucedida no Brasil depende da superação de desafios jurídicos e da implementação de medidas que assegurem a segurança jurídica e a proteção dos direitos das partes envolvidas.
This paper proposes an integrated fintech–insurtech architecture that embeds insurance directly into logistics and trade workflows using digital networks, distributed ledger technologies, and real-time risk analytics. Drawing on network effects, game theory, and empirical observations from inland transport and cargo insurance markets in India, the paper models strategic interactions among insurers, shippers, transporters, and trade finance providers. The study introduces an ordinal risk classification framework and a self-sustaining quarterly cargo claims cycle designed to stabilize liquidity, optimize premium pricing, and reduce information asymmetry, particularly for MSMEs operating in fragmented supply chains. By repositioning insurance as a continuously embedded financial infrastructure rather than a post-loss settlement mechanism, the framework demonstrates how digitally native insurance systems can improve trust, capital efficiency, and resilience across integrated logistics and trade ecosystems.
The ontological issues such as the concept, features, and attributes of smart contracts written in code and running on the blockchain have been the focus of research in the academic community.In this paper, we first construct a smart contract illegal behavior determination model based on the C4.5 decision tree algorithm, which realizes accurate prediction and determination of illegal behaviors existing in smart contract transactions by extracting multiple attribute features of smart contract transaction data.Then, the correlation between smart contract features and contract risk is analyzed by Pearson coefficient, and the risk assessment evaluation system of smart contract performance is constructed by using hierarchical analysis.Finally, the fulfillment path of smart contract is proposed by synthesizing all the analysis results.Among the 24 randomly selected samples, the total prediction probability of the illegal behavior determination model based on the C4.5 decision tree algorithm reaches 95.83%, which is able to effectively identify the illegal behavior of smart contracts.The Pearson chi-square value between smart contract features and contract risk is 224.6317, and the Sig.(two-tailed) value is 0.000, indicating that there is a significant correlation between the two.By constructing a smart contract risk assessment index system, this paper designs a dynamic monitoring model of smart contract fulfillment risk level, and proposes a smart contract fulfillment path from the aspects of reasonable allocation of legal responsibility and legal regulation of contract fulfillment.
This study provides a bibliometric analysis of the research trends in financial derivatives within the banking and finance literature. By examining citation patterns, co-authorship networks, and keyword co-occurrences, the study identifies key research themes and their evolution over time. The analysis reveals the central role of derivatives in risk management and financial stability, particularly in the wake of financial crises. It highlights the growth of computational techniques in derivatives pricing and risk management, with an increasing focus on advanced models and simulations. The study also explores the emerging influence of blockchain technology and decentralized finance in reshaping the derivatives landscape. The bibliometric map underscores the global nature of financial derivatives research, with significant contributions from the United States, China, and the United Kingdom. The study provides valuable insights for scholars, practitioners, and policymakers, suggesting areas for further research, particularly in regulatory frameworks, pricing models, and the integration of new technologies in the derivatives market.
Abstract Smart contracts and blockchain technology have revolutionized our transactions and interactions with digital systems, yet their vulnerabilities can lead to devastating consequences such as financial losses, data breaches, and compromised system integrity. Existing detection methods, including static analysis, dynamic analysis, and machine learning-based approaches, have their limitations, such as requiring large amounts of labeled data or being computationally expensive. To address these limitations, we propose a novel approach that leverages a One-Class Variational Autoencoder (VAE) with CodeBERT for data pre-processing to detect vulnerabilities in smart contracts. Our approach achieved a higher F1 score (88.93%) compared to the baselines evaluated, even when labeled data is limited. This paper contributes to the development of effective and efficient vulnerability detection methods, ultimately enhancing the security and reliability of smart contracts and blockchain-based systems. By demonstrating superior performance in imbalanced data scenarios, our method offers a practical solution for real-world applications in blockchain security.
This article examines the integration of blockchain technology and smart contracts within financial regulatory systems and their potential to transform traditional compliance frameworks. The distributed and immutable nature of blockchain presents unique opportunities for enhancing regulatory reporting, fraud detection, and compliance monitoring in financial institutions. Through analysis of implementation cases and theoretical frameworks, this article identifies key applications in automated reconciliation, real-time monitoring, and cross-border regulatory coordination. Despite promising benefits in transparency and automation, significant challenges persist in scalability, legacy system integration, and regulatory uncertainty. This article contributes to the growing body of literature on regulatory technology by providing a comprehensive examination of blockchain applications in financial oversight, offering insights for both regulatory bodies and financial institutions navigating this technological transition. The articles suggest that while blockchain implementation requires substantial infrastructure adaptation, its potential to create more efficient, transparent, and secure regulatory systems warrants continued exploration and development.
Financial data analytics has become a critical tool for businesses seeking to drive growth, enhance fraud prevention, and mitigate risks in dynamic markets. By leveraging large datasets, advanced algorithms, and real-time analytics, organizations can make more informed financial decisions, improve operational efficiency, and enhance compliance with regulatory frameworks. This review explores how financial data analytics contributes to business growth by improving revenue forecasting, identifying market trends, and optimizing financial planning. Companies can leverage predictive models and artificial intelligence to gain competitive advantages through better risk assessment and investment decision-making. Fraud prevention is another key area where financial data analytics plays a transformative role. Machine learning algorithms, anomaly detection systems, and real-time transaction monitoring help identify and prevent fraudulent activities before they cause significant financial losses. Businesses and financial institutions can use automated risk-scoring models to strengthen security in banking, payments, and investment transactions. Risk mitigation in financial markets is also enhanced through data analytics. By employing predictive modeling, scenario analysis, and stress testing, businesses can assess potential market fluctuations and develop strategies to minimize financial exposure. Moreover, analytics-driven regulatory compliance mechanisms improve transparency and reporting, ensuring adherence to legal and industry standards. Despite its advantages, financial data analytics faces challenges such as data privacy concerns, integration with legacy systems, and the need for skilled professionals. However, emerging technologies, including blockchain, AI, and decentralized finance (DeFi), present new opportunities for strengthening financial security and business resilience. This review concludes that financial data analytics is a vital asset for modern businesses, offering strategic insights that drive profitability, enhance fraud detection, and strengthen risk management. Companies must continue to invest in data-driven solutions to stay competitive in an increasingly digital financial landscape. Keywords: Financial data, Business growth, Fraud prevention, Markets.
Embedded finance represents a transformative shift in how financial services integrate within non-financial platforms, creating seamless user experiences that eliminate traditional friction points. This comprehensive article explores how companies have leveraged embedded payment infrastructures to create extensive ecosystems that transcend their original business models. The technical infrastructure powering these innovations—including API-first banking, regulatory technology, and microservices architecture—enables real-time processing at scale while maintaining security and compliance. The evolution toward Super Apps demonstrates how financial transactions can become invisible utilities within broader digital experiences, while artificial intelligence enhances these platforms through predictive analytics and conversational interfaces. Despite technical challenges related to data security, scalability, and cross-border complexity, emerging trends including decentralized finance integration, context-aware services, and embedded insurance promise continued innovation in this rapidly developing field
This study proposes a decentralized framework that merges smart contract based Decentralized Finance (DeFi) protocols and traditional Enterprise Resource Planning (ERP) systems to provide secure, automatic, and verifiable transaction execution. It constructs an additional middleware interface to guarantee interoperability between ERP modules and blockchain networks that utilize smart contracts for procurement, finance, and asset management modules. The system was tested empirically within a hybrid testbed of chains with Ethereum Virtual Machine (EVM) compatibility simulation executing ERP transaction testing on a simulated environment with physical hardware. According to quantitative assessment results, performance increased, achieving a 38% increase in transaction throughput, a 27% decrease in execution costs, increased trust and traceability due to cryptographic audit trails, and improved auditability. The research highlights the potential of DeFi integrated ERP systems for decentralized enterprise finance systems as a scalable secure replacement to centralized enterprise finance systems.
The rapid development of automation and artificial intelligence (AI) is causing a significant upheaval in the banking sector.These technological advancements are boosting client experiences, increasing financial efficiency, and altering the way banks function.With an emphasis on topics like fraud detection, risk management, customer service (think chatbots and virtual assistants), personalized banking, and automating repetitive processes, this study examines how banks are presently utilizing AI and automation.While highlighting the major advantages-such as reducing expenses, reducing mistakes, and expediting decision-making-it also addresses the drawbacks, including concerns about data privacy, maintaining regulatory compliance, and the effect on employment.According to the study, further integration of technologies such as robotic process automation (RPA), machine learning, and natural language processing is anticipated in the future, which will increase the intelligence and adaptability of banking systems.Also, it looks at new developments that have the potential to drastically change the sector, such as open banking, decentralized finance (DeFi), and AI-powered predictive analytics.As the report concludes, banks must carefully consider ethical issues, make investments in staff upskilling, and figure out how humans and computers can collaborate efficiently, even though AI and automation present enormous prospects for innovation and expansion.Although the banking industry has a bright future, maximizing the potential of new technologies will require careful planning.
The non-fungible tokens (NFTs) market has evolved over the past decade, with NFTs serving as unique digital iden-tifiers on a blockchain that certify ownership and authenticity. The trading attributes of NFTs have drawn many users and investors. However, their high value also attracts attackers who exploit vulnerabilities in NFT smart contracts for illegal profits, thereby harming the NFT ecosystem. One notable vulnerability in NFT smart contracts is sleep minting, which allows attackers to illegally transfer others' tokens. Although some research has been conducted on sleepminting, these studies are basically qualitative analyses or based on historical transaction data. There is a lack of understanding from the contract code perspective, which is crucial for identifying such issues and preventing attacks before they occur. To address this gap, in this paper, we categorize the sleep-minting issue and find four distinct types of sleepminting in NFT smart contracts. Each type is accompanied by a comprehensive definition and illustrative code examples to provide a clear understanding of how these vulnerabilities manifest within the contract code. Furthermore, to help detect the defined defects before the sleepminting problem occurrence, we propose a tool named WakeMint, which is built on a symbolic execution framework. WakeMint is designed to be compatible with both high and low versions of Solidity, ensuring broad applicability across various smart contracts. The tool also employs a pruning strategy to shorten the detection period. Additionally, WakeMint gathers some key information, such as the owner of an NFT and emissions of events related to the transfer of the NFT's ownership during symbolic execution. Then, it analyzes the features of the transfer function based on this information so that it can judge the existence of sleepminting. We ran WakeMint on 11,161 real-world NFT smart contracts and evaluated the results. We found 115 instances of sleep minting issues in total, and the precision of our tool is 87.8 %.
In this era, significant transformations in industries and tool utilization are driven by AI/Large Language Models (LLMs) and advancements in Machine Learning. There's a growing emphasis on Machine Learning Operations(MLOps) for managing and deploying these AI models. Concurrently, the imperative for richer smart contracts and on-chain computation is escalating. Our paper introduces an innovative framework that integrates blockchain technology, particularly the Cosmos SDK, to facilitate on-chain AI inferences. This system, built on WebAssembly (WASM), enables interchain communication and deployment of WASM modules executing AI inferences across multiple blockchain nodes. We critically assess the framework from feasibility, scalability, and model security, with a special focus on its portability and engine-model agnostic deployment. The capability to support AI on-chain may enhance and expand the scope of smart contracts, and as a result enable new use cases and applications.
Smart contracts are at the core of blockchain technology, but the cost of fixing their security vulnerabilities is high, making pre-deployment vulnerability detection crucial. Existing methods rely on fixed rules, which have limitations in accuracy and scalability, and their efficiency decreases with the complexity of the rules. Neural-network-based methods can identify some vulnerabilities but are inefficient in multi-vulnerability scenarios and depend on source code. To address these issues, we propose a multi-vulnerability-based smart contract detection method called RTMS. RTMS takes bytecode as input, disassembles it into opcodes, uses the gas consumed by the contract for data slicing, and extends the length of input opcodes through a layered structure. It employs a weighted binary cross-entropy (BCE) function to handle data imbalance and combines channel-sequence attention mechanisms to extract vulnerability correlation features. By using transfer learning, it reduces training parameters and computational costs. Our RTMS model can detect multiple vulnerabilities simultaneously, enhancing detection accuracy and efficiency. In experiments with 100,000 real contract samples, the model achieved a Jaccard coefficient of 0.9312, a Hamming loss of 0.0211, and an F1 score that improved by about 11 percentage points compared to existing models, demonstrating its superiority and stability.
Financial technology (fintech) faces growing demands for faster data processing, reduced delays, and better security as the sector rapidly advances. Current centralized systems are vulnerable to various threats including data manipulation, service outages, and security breaches that can compromise financial transactions. This research examines how combining blockchain technology, smart contracts, and machine learning could solve key challenges in fintech-related to security, transparency, and operational performance. The study also considers how these technologies affect regulatory compliance, legal frameworks, and ethical oversight. The research methodology involves analyzing ten years of literature on blockchain in fintech, specifically focusing on decentralized ledgers, automated smart contracts, and machine learning for data analysis. The findings are presented visually through diagrams and data visualizations that demonstrate improvements in operations, security, and cost efficiency. The study shows that blockchain provides transparent, secure financial record-keeping through its decentralized structure. Smart contracts help reduce costs and make financial services more accessible to underserved groups by automating processes. Machine learning enhances these blockchain applications by enabling predictive analysis and data-driven choices. While progress has been significant, there are still obstacles to overcome, particularly in developing governance frameworks that ensure ethical use and regulatory compliance. This analysis contributes to new understanding by examining how blockchain and machine learning work together in fintech, with special attention to previously understudied areas like operational efficiency, security, and regulatory compliance. The research outlines how these technologies can transform finance while providing practical solutions to current challenges, working toward a more secure, inclusive, and efficient financial system.
Yackolley Amoussou-Guenou, Maurice Herlihy, Sucharita Jayanti, Maria Potop-Butucaru · 5 authors
Many of the problems that arise in the context of blockchains and decentralized finance can be seen as variations on classical problems of distributed computing. The smart contract model proposed here is intended to capture both the similarities and the differences between classical and blockchain-based models of distributed computing. The focus is on cross-chain protocols in which a collection of parties, some honest and some perhaps not, interact through trusted smart contracts residing on multiple, independent ledgers. While cross-chain protocols are capable of general computations, they are primarily used to track ownership of assets such as cryptocurrencies or other valuable data. For this reason, the smart contract model differs in some essential ways from familiar models of distributed and concurrent computing. Because parties are potentially Byzantine, tasks to be solved are formulated using elementary game-theoretic notions, taking into account the utility to each party of each possible outcome. As in the classical model, the parties provide task inputs and agree on a desired sequence of proposed asset transfers. Unlike the classical model, the contracts, not the parties, determine task outputs in the form of executed asset transfers, since they alone have the power to control ownership.
Smart contracts are essential to decentralized finance (DeFi) and blockchain ecosystems but are increasingly vulnerable to exploits due to coding errors and complex attack vectors. Traditional static analysis tools and existing vulnerability detection methods often fail to address these challenges comprehensively, leading to high false-positive rates and an inability to detect dynamic vulnerabilities. This paper introduces SmartLLM, a novel approach leveraging fine-tuned LLaMA 3.1 models with Retrieval-Augmented Generation (RAG) to enhance the accuracy and efficiency of smart contract auditing. By integrating domain-specific knowledge from ERC standards and employing advanced techniques such as QLoRA for efficient fine-tuning, SmartLLM achieves superior performance compared to static analysis tools like Mythril and Slither, as well as zero-shot large language model (LLM) prompting methods such as GPT-3.5 and GPT-4. Experimental results demonstrate a perfect recall of 100% and an accuracy score of 70%, highlighting the model's robustness in identifying vulnerabilities, including reentrancy and access control issues. This research advances smart contract security by offering a scalable and effective auditing solution, supporting the secure adoption of decentralized applications.
This research explores the impact of Non-Fungible Token (NFT) authentication on purchase intention in new and pre-loved luxury markets, grounded in warranting theory and institution-based trust theory. Using a two-study online experimental design (Study 1: new luxury market, Study 2: pre-loved luxury market), both studies used a one-factor (NFT authentication) and two-level (yes or no) design and PROCESS macro Model 6 for serial mediation analysis. The results from Study 1 indicate that NFT authentication enhances purchase intention through increased warranting value and structural assurance. Study 2 confirmed these serial mediating effects and revealed a direct significant impact of NFT authentication in the pre-loved luxury market, which was not significant in the new luxury market. This study highlights the importance of NFT authentication in enhancing consumer trust and purchase intention in both new and pre-loved luxury markets.
цель исследования – проанализировать влияние и будущие развитие альтернативного варианта централизированной страховой отрасли, который в научной литературе именуется как децентрализированное страхование. Децентрализованное страхование, также известно как страхование на основе блокчейна, является революционной концепцией, возникшей с появлением технологии блокчейн. Произвести разбор пробелов дизайна продуктов децентрализированного страхования в рыночной практике страхования и теоретических моделей распределения рисков в литературе. И на основе данного анализа и разбора представить общую структуру модели взаимного страхования в здравоохранении, которую можно было бы применять для разработки на платформах децентрализованных финансов, и математическую основу для описания общих свойств. Так же дать общее представление о понятии (де)централизации. вытекающее из архитектуры блокчейн технологии. Методологической базой исследования служат общенаучные методы исследования: логика, синтез, анализ, индукция, дедукция, а также агентно-ориентированный подход к анализу страховой отрасли. Результаты. Определен один из подходов к разработке модели децентрализированного страхования как части системы децентрализированных финансов и многоагентному моделированию страховых взаимодействий в направлении их улучшения качественности и безопасности. В рамках предложенной модели установлено, что критерием эффективности ее алгоритма служит низкое потребление ресурсов на поддержку платформы, вектор работы в целом направлен в сторону страхователей в отличии от централизированного страхования, где он направлен в сторону страховой компании и все свойства присущи блокчейн технологиям. Вывод. По мере того, как эта концепция децентрализированного страхования развивается и созревает, она может изменить страховую отрасль, расширяя возможности отдельных лиц и организаций для более эффективного управления рисками, одновременно укрепляя доверие и подотчетность среди участников. the purpose of the study is to analyze the impact and future development of an alternative version of the centralized insurance industry, which is referred to in the scientific literature as decentralized insurance. Decentralized insurance, also known as blockchain-based insurance, is a revolutionary concept that emerged with the advent of blockchain technology. To analyze the gaps in the design of decentralized insurance products in the insurance market practice and theoretical models of risk distribution in the literature. And based on this analysis and analysis, to present the general structure of the mutual insurance model in healthcare, which could be used for development on decentralized finance platforms, and a mathematical basis for describing common properties. Also give a general idea of the concept of (de)centralization. stemming from the architecture of blockchain technology. The methodological basis of the research is general scientific research methods: logic, synthesis, analysis, induction, deduction, as well as an agent-oriented approach to the analysis of the insurance industry. Results. One of the approaches to the development of a model of decentralized insurance as part of a system of decentralized finance and multi-agent modeling of insurance interactions in the direction of improving their quality and safety is defined. Within the framework of the proposed model, it was found that the criterion for the effectiveness of its algorithm is low resource consumption to support the platform, the vector of work is generally directed towards policyholders, unlike centralized insurance, where it is directed towards the insurance company and all the properties are inherent in blockchain technologies. Conclusion. As this concept of decentralized insurance develops and matures, it can transform the insurance industry by empowering individuals and organizations to manage risks more effectively, while strengthening trust and accountability among participants.
The complexities of modern financial markets, characterized by heightened volatility and uncertainty, have necessitated the evolution of advanced risk management strategies. As global markets become increasingly interconnected, financial institutions, investors, and policymakers face unprecedented challenges in identifying, assessing, and mitigating risks. Effective risk management has emerged as a cornerstone of financial stability, requiring a blend of traditional methods and innovative tools. This paper explores comprehensive strategies for navigating volatility in complex financial environments, addressing systemic, credit, market, and operational risks. Traditional approaches, such as portfolio diversification and value-at-risk (VaR) modelling, remain foundational but are now complemented by cutting-edge technologies, including artificial intelligence (AI), machine learning (ML), and big data analytics. These tools enable real-time monitoring, predictive analytics, and stress testing, enhancing the capacity to anticipate and respond to emerging threats. Additionally, the integration of blockchain technology offers improved transparency and resilience in financial transactions, further mitigating systemic vulnerabilities. Case studies from diverse sectors highlight the practical applications of these strategies, illustrating how robust risk management frameworks can minimize losses, enhance profitability, and ensure regulatory compliance. The paper also examines the role of regulatory frameworks in shaping risk management practices and emphasizes the importance of a proactive, adaptive approach in navigating volatile market conditions. By combining traditional methodologies with technological advancements, financial institutions can build resilient systems capable of withstanding shocks and fostering long-term stability. This paper concludes by identifying emerging trends, such as quantum computing and decentralized finance, as transformative forces likely to redefine risk management in the future.
Automated Program Repair (APR) for smart contract security promises to automatically mitigate smart contract vulnerabilities responsible for billions in financial losses. However, the true effectiveness of this research in addressing smart contract exploits remains uncharted territory. This paper bridges this critical gap by introducing a novel and systematic experimental framework for evaluating exploit mitigation of program repair tools for smart contracts. We qualitatively and quantitatively analyze 20 state-of-the-art APR tools using a dataset of 143 vulnerable smart contracts, for which we manually craft 91 executable exploits. We are the very first to define and measure the essential "exploit mitigation rate" , giving researchers and practitioners a real sense of effectiveness of cutting edge techniques. Our findings reveal substantial disparities in the state of the art, with an exploit mitigation rate ranging from a low of 29% to a high of 74%. Our study identifies systemic limitations, such as inconsistent functionality preservation, that must be addressed in future research on program repair for smart contracts.