Blockchain Papers

Befoum Stephane Richard, Jianbin Gao, Qi Xia, Kombou Victor · 6 authors

No abstract is available for this record.

Son, Do Hai, Hieu, Le Vu, Khoa, Tran Viet, Alem, Yibeltal F. · 8 authors

Blockchain technology has experienced rapid growth and has been widely adopted across various sectors, including healthcare, finance, and energy. However, blockchain platforms remain vulnerable to a broad range of cyberattacks, particularly those aimed at exploiting transactions and smart contracts (SCs) to steal digital assets or compromise system integrity. To address this issue, we propose a novel and effective framework for detecting cyberattacks within blockchain systems. Our framework begins with a preprocessing tool that uses Natural Language Processing (NLP) techniques to transform key features of blockchain transactions into image representations. These images are then analyzed through vision-based analysis using Vision Transformers (ViT), a recent advancement in computer vision known for its superior ability to capture complex patterns and semantic relationships. By integrating NLP-based preprocessing with vision-based learning, our framework can detect a wide variety of attack types. Experimental evaluations on benchmark datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods in terms of both accuracy (achieving 99.5%) and robustness in cyberattack detection for blockchain transactions and SCs.

Yafei Liu, Yuling Chen, Bo Li, Yuxiang Yang · 5 authors

No abstract is available for this record.

Selyan Bounouar, Beomjoong Kim, Jung­hee Lee

Blockchain technology enables semi-anonymous transactions, where user identities are not directly revealed but instead linked to cryptographic wallet addresses. While this design enhances privacy and security, the intrinsic transparency of public blockchains raises concerns about the true anonymity of users. To address this, privacy-enhancing techniques such as CoinJoin were developed to obscure transaction flows. CoinJoin is a Bitcoin-based mixing technique that combines multiple inputs and outputs into a single larger transaction, making it difficult to trace the original senders and recipients. Although CoinJoin was intended to support privacy-preserving transactions, it is often exploited for money laundering. As a result, there is a growing need to identify CoinJoin transactions in order to prevent such misuse. This research aims to detect unidentified CoinJoin transactions on the Bitcoin blockchain using a machine learning approach. Unlike prior work that relied on heuristics or traditional machine learning algorithms, we propose an improved methodology relying on random forest ($\mathbf{R F}$) models designed to handle imbalanced datasets. Specifically, we introduce a novel variant, the biased random forest (BRAF), aimed at improving detection performance under significant class imbalance.

Giovanni Ciaramella, Fabio Martinelli, Francesco Mercaldo, Paolo Mori · 5 authors

Blockchain adoption has significantly expanded in recent years, with the emergence of smart contracts facilitating practical applications in many domains. Since smart contracts can execute cryptocurrency transfers, malicious users have started implementing fraudulent smart contracts to deceive blockchain users and steal their funds. To mitigate this issue, this paper proposes an approach to detect fraudulent smart contracts leveraging Federated Machine Learning. Our approach generates an image representation for each smart contract by extracting the opcodes and assigning a unique RGB pixel. We utilized two publicly available datasets, including malicious and trustworthy smart contracts, to train multiple models on non-independent and Identically Distributed data to better represent a real-world scenario, achieving interesting results in accuracy. To the best of our knowledge, this article represents the first approach in the unique identification of fraudulent smart contracts using opcodes with a specific color, also leveraging a Federated Machine Learning approach in the blockchain environment.

Ankur Jain, Somanath Tripathy

Detecting fraudulent transactions in Ethereum is challenging due to the evolving tactics of malicious actors and the complexity of blockchain transactions. This work constructs a proximity-aware graph (PAG) for each Ethereum account, where each node is connected to its transactional neighbours within two hops to capture financial interactions effectively. For better performance, EthAegis integrates both local graphical features and global transactional properties of each proximity-aware graph (PAG).To effectively capture the graphical and transactional relationships between Ethereum accounts, Graph Sample and Aggregate (GraphSAGE) are deployed. It is a Graph Neural Network (GNN) based model that is optimised for inductive learning on large-scale graphs. It is observed that EthAegis could effectively capture hidden patterns and anomalies in Ethereum transactions by considering both the transactional and graphical characteristics. Experimental evaluations on real Ethereum transaction data demonstrate that this method significantly improves fraud detection accuracy while ensuring scalability, providing a robust and adaptive solution to secure blockchain transactions. The proposed model achieves an accuracy of 0.9908, precision of 0.9922, recall of 0.9894, and F1-score of 0.9908 on the Ethereum transactional dataset.

Fatih Ertam

Blockchain technologies have profoundly transformed information systems by providing decentralized infrastructures that enhance transparency, security, and traceability. Ethereum, in particular, supports smart contracts and facilitates the development of decentralized finance (DeFi), non-fungible tokens (NFTs), and Web3 applications. However, its openness also enables illicit activities, including fraud and money laundering, through anonymous wallets. Identifying wallets involved in large transfers or abnormal transactional patterns is therefore critical to ecosystem security. This study proposes an AI-based framework employing XGBoost, LightGBM, and CatBoost to detect suspicious Ethereum wallets, achieving test accuracies between 95.83% and 96.46%. The system provides near real-time predictions for individual or recent wallet addresses using a pre-trained XGBoost model. To improve interpretability, SHAP (SHapley Additive exPlanations) visualizations are integrated, highlighting the contribution of each feature. The results demonstrate the effectiveness of AI-driven methods in monitoring and securing Ethereum transactions against fraudulent activities.

Girish Kumar

Traditional centralized systems often fail to prevent fraud and ensure data integrity, especially as cyber threats grow more complex. This paper proposes a blockchain-based framework enhanced with artificial intelligence to address these limitations. Blockchain provides secure, tamper-proof storage and smart contract–based access control, while AI enables realtime anomaly detection by analyzing behavioral patterns. The system is built using Ethereum smart contracts and machine learning models, with a modular architecture connecting frontend, backend, and AI components. Evaluation shows over 92% accuracy in fraud detection, efficient response times, and reliable audit trails. The approach proves scalable and suitable for sensitive sectors such as healthcare and finance, offering a secure, intelligent, and decentralized solution for modern data protection

Gyuyeon Na, Minjung Park, Hyeonjeong Cha, Soyoun Kim · 9 authors

Blockchain transaction networks are complex, with evolving temporal patterns and inter-node relationships. To detect illicit activities, we propose a hybrid GCN-GRU model that captures both structural and sequential features. Using real Bitcoin transaction data (2020-2024), our model achieved 0.9470 Accuracy and 0.9807 AUC-ROC, outperforming all baselines.

Ali M. Emran, Md Kamrul Islam -, Md Ashraful Islam Nayem -, Md Rubel · 5 authors

Abstract: Exploring GNNs as a cutting-edge approach to real-time detection of online money transfer fraud is the focus of this work. P2P payment systems, mobile money platforms, and decentralized financial infrastructures (DeFi) have all experienced explosive growth over the past decade due to their simplicity, speed, and affordability. Identity fraud, synthetic account misuse, coordinated fraud rings that exploit systemic vulnerabilities, and transaction laundering are some of the new types of fraud that can occur in these platforms, despite their desirability. In situations where fraud is predictable, isolated, and statistically distinct, logistic regression, rule-based algorithms, and standard ML models like Random Forests and SVMs have all proved effective in detecting it. Modern, hyper-connected, real-time financial ecosystems are seeing an uptick in non-linear, relational, and temporal fraud patterns, which these tactics struggle to combat. Because of their inherent bias, they fail to recognize the interconnected structural and relational processes that may point to coordinated fraud. The graph-like qualities of monetary exchanges, where elements (like IP addresses, users, and devices) are organically linked through edges that stand for transactions or relationships, are utilized by Graph Neural Networks to give a paradigm shift, on the other hand. Generalized neural networks (GNNs) are crucial for uncovering intricate fraud schemes because they represent these interactions as a graph structure that permits data to travel and accumulate across nodes. Because of this, the model may take global and regional effects into consideration. Relational learning excels when other methods fail, such as when trying to detect suspicious clusters of transactions, multi-hop collusions, or fraudulent subnetworks using separate features. In order to implement this method, we constructed an entirely new fraud detection system utilizing GNNs. Node feature engineering, graph generation, classification heads, message-passing layers, and a real-time processing optimized pipeline are all parts of it. We were able to empirically evaluate our technique using a real-world transactional dataset that was acquired from a leading financial services provider. As is typical in fraud detection tasks, the dataset had a highly skewed class distribution, which impacted both memory and accuracy. With an F1-score of 0.78, accuracy of 98.7 percent, precision of 0.81%, and recall of 0.76%, the model nevertheless performed admirably. The model's ability to detect fraudulent behaviors while maintaining dependable operations in the real world is demonstrated by these measures. Beyond its implications for technological performance, this study will help achieve broader aims in regulation, ethics, and national security. A number of federal agencies have issued advisories highlighting the need for strong, intelligent, and real-time fraud monitoring systems to safeguard national financial systems from fraudulent exploitation. These agencies include the DOJ, FinCEN, and DHS. Compliance with the USA PATRIOT Act and the Bank Secrecy Act (BSA) is of the utmost importance to financial institutions and fintech enterprises. As stated in the National Strategy to Combat Terrorist and Other Illicit Financing, they also want AI-driven surveillance systems to be resilient and explainable. This national goal is helped by our study, which provides a scalable, interpretable, and performance-driven GNN-based system. Along with helping with auditability, model explainability, and compliance reporting, all of which are crucial for regulated businesses, this strategy also helps with effective fraud detection. Integrating our suggested architecture for decentralized, privacy-preserving fraud detection into online learning extensions can further improve their functionality. Over time, these extensions can be integrated with federated learning systems and streaming data platforms. This work puts GNNs in a position to become a new weapon in the fight against digital payment fraud by combining cutting-edge graph representation learning with cybersecurity regulations and goals for financial integrity. Thanks to our research's careful analysis, innovative architecture, and adherence to statutory criteria, future financial systems will be reliable, safe, and robust. Additionally, it resolves a significant technical matter.

Teoman Berkay Ayaz, Muhammet Furkan Özara, Ahmet Erkan Çelik, Akhan Akbulut

Blockchain systems promote transparency, decentralization, and reliability. Nevertheless, they remain vulnerable to more sophisticated fraudulent actors, particularly on newly launched platforms with little or nonexistent transaction histories. This paper introduces an innovative hybrid learning model that integrates few-shot learning with active learning to address two fundamental issues in fraud detection within financial systems: the limited availability of annotated fraud data and the ongoing evolution of illegal behavior. The study provides a comprehensive evaluation of two complementary datasets: a public dataset comprising real-life transactions obtained from Kaggle to establish a generalizable benchmark (9,841 transactions, 22.1% fraudulent) and a custom synthetic dataset designed for the PointXchange platform (197,458 transactions, 0.16% fraudulent). The approach we use generates balanced training sets and minimizes annotation costs by sampling as few as 8 to 128 samples per class and iteratively querying an oracle for useful labels. Benchmarks conducted across four families of algorithms: gradient boosting machines (XGBoost, LightGBM, CatBoost), boosting (AdaBoost), ensemble learners (Random Forest, Extra Trees), and neural networks (MLP, XNet), demonstrate the effectiveness of the proposed approach with recall scores reaching up to 0.9906.

Arash Habibi Lashkari, Sepideh HajiHosseinKhani, J.M.V. Duarte, Isabella Lopez · 6 authors

With the shift from Centralized Finance (CeFi) to Decentralized Finance (DeFi), financial transactions have become trustless and self-executing through blockchain platforms, creating new opportunities while exposing the ecosystem to significant fraud risks. However, due to the lack of centralized oversight and the vulnerabilities in the blockchain platforms, DeFi transactions still face several security challenges, including fraud, identity theft, insider threats, and data breaches. Various methods, including regulatory frameworks, machine learning (ML), and deep learning (DL) techniques, are employed to detect these threats, particularly fraud, in DeFi transactions. Although these approaches help identify fraudulent activities, they face challenges related to accuracy and zero-day attacks due to insufficient data and the complexity of emergingfraud patterns. This study presents a novel approach for detecting and profiling fraud attacks, including zero-day ones in DeFi transactions, thereby eliminating the reliance on wallet transaction history, a limitation that previous research has heavily depended on. The proposed approach leverages two key components: a novel analyzer named DeFiTransLyzer (V1.0) and an Advanced Genetic Algorithm (AGA) for fraud transaction profiling. DeFiTransLyzer extracts 79 features from transaction and wallet data. At the same time, the AGA incorporates advanced techniques, including Penalized Fitness Evaluation, Elite Retention Strategy, Dynamic Mutation Rate, and dynamic generation, to create precise fraud profiles. By focusing solely on transaction features, the model ensures that all fraudulent activities, including zero-day ones, initiated within the first transaction of a new account can be effectively detected, without relying on prior wallet activity. To address the scarcity of comprehensive validation datasets, we introduce BCCCDeFiFraudTrans-2025, which comprises 1,026,867 annotated Ethereum transaction samples from the DeFi ecosystem. Additionally, the study establishes two taxonomies for systematic classification, covering the literature on fraud detection and profiling methods. Experimental results demonstrate that the proposed method achieves superior accuracy, precision, and efficiency while offering interpretability through its profiling mechanism. These promising outcomes highlight the potential of AGA profiling to enhance the detection and identification of fraudulent activities, including zero-day ones within DeFi transactions, contributing to the security and resilience of blockchainbased financial systems.

Pedro Leale, Ivan da Silva Sendin

Este trabalho apresenta uma metodologia de detecção de contratos inteligentes do tipo mixers na rede Ethereum. Utilizou-se um modelo de aprendizado de máquina baseado em Random Forest, treinado com transações do Tornado Cash e balanceado com amostras de 100 endereços aleatórios não relacionados a mixers. O modelo foi treinado com dados de março de 2025 e validado em 29/10/2020, dia de alto volume de transações, identificando corretamente 3 endereços do Tornado Cash.

Ziyi Xiong, Rong Liu, Hemang Subramanian

No abstract is available for this record.

Karan Maheshwari, Srujan Kumar Ch., Y. V. Srinivasa Murthy, Anand Paul

Phishing attacks in Ethereum transactions pose a significant threat to the security and integrity of blockchain-based systems, as these scams exploit user vulnerabilities to extract sensitive information or cryptocurrency assets. In contrast to the approaches proposed by the various research works to tackle phishing detection, many struggle with high-dimensional datasets, leading to computational inefficiencies and overfitting. To address these gaps, this study applies principal component analysis (PCA) for dimensionality reduction, helping in the development of more efficient and robust machine learning models by reducing data complexity and enhancing model generalization. A comparative analysis is conducted using multiple algorithms, including support vector machines (SVMs), decision trees (DT), XGBoost, and multi-layer perceptron (MLP). By evaluating their performance using standard metrics such as accuracy, F1 score, precision, recall, and ROC-AUC, the MLP model demonstrates superior accuracy and generalization, establishing its efficacy for phishing detection in Ethereum transactions. This work highlights the importance of feature reduction techniques and neural network models in enhancing the accuracy and efficiency of phishing detection systems, paving the way for future advancements in blockchain security.

Vasavi Chithanuru, Mangayarkarasi Ramaiah, Vanmathi Chandrasekaran

Ethereum's distributed ledger technology operates on decentralized principles that have transformed how digital assets are exchanged. Yet the platform's underlying design contains security weaknesses that expose users to multiple forms of malicious activity, such as fraudulent wallet schemes, network identity manipulation, pyramid financial structures, and service interruption attacks. This study aims to address the cyber-attacks on the Ethereum platform by developing an innovative ensemble machine-learning framework based on a refined feature set derived from real-time Ethereum transactions. The proposed framework employed a method that encapsulates the feature selection process, leveraging the advantages of machine learning algorithms to derive the refined feature set. The conducted experiment employs Random Forest and XGBoost, to identify the significant features. To mitigate the overfitting issue in the proposed machine learning model, the SMOTEENN (Synthetic Minority Oversampling Edited Nearest Neighbors) technique, has applied. The experimental results reveal that the proposed model exceeds the performance of existing fraud detection approaches, achieving a 99.4% accuracy and a Matthews Correlation Coefficient (MCC) of 94.9%.

Pushpakumar R, S. Sathishkumar, G. Dheepak, G. Amirthayogam · 6 authors

Due to the increased levels of cryptocurrency transactions, novel frameworks are required to detect fraud in the real-time and make decentralized finance safe. It is suggested in this paper that SecureChainNet, which encompasses both CNNs and LSTM networks, would aid in the detection of fraud in cryptocurrency networks. The first phase involves the use of CNNs to discover difficult patterns within the structured transactions data that is largely undetected by traditional means. Subsequently, the transaction sequence is analyzed using LSTM module, which enhances the system to identify fraud patterns thus developing over time. When used together with blockchain, all the decisions made by a model are recorded into an immutable log, and the following auditing process reconfirms decentralized data verification and increased trust. Experimentally, SecureChainNet has been determined to possess a significantly higher degree of accuracy, precision, and recall compared to other methods when putting it to use with the real blockchain data. Additionally, the system has the capability of operating almost in real-time and so it can be used to trade cryptocurrencies being traded. The analysis notes that deep learning in conjunction with blockchain security has the potential of creating intelligent and dependable financial fraud systems.

Dheeraj Kumar, Marimuthu Palaniswami, Vallipuram Muthukkumarasamy

Ponzi schemes, a more than a century-old fraud, have recently infiltrated blockchain-based cryptocurrency domain led by an explosion of such schemes in two most popular cryptocurrencies: Bitcoin and Ethereum. On these two platforms alone, the perpetrators of these frauds have fleeced gullible investors of billions of dollars annually. Smart Ponzi schemes are a hazard to these cryptocurrency ecosystems, diminishing investor confidence in these cutting-edge technologies, threatening their integrity, and hindering their growth and broader adaptation. These smart Ponzi schemes have also created a nightmare for law enforcement as tracking and taking countermeasures against fraudsters and recovering the victims’ investment is challenging. Over the years, researchers have utilized significant advances in machine learning and AI to detect and promptly caution users against investing in Ponzi schemes on Bitcoin and Ethereum. However, this research still exists in silos, and there is a lack of a detailed survey paper critically analyzing various aspects of the approaches focusing on the menace of smart Ponzi schemes. This article surveys the state-of-the-art techniques proposed in the literature to detect smart Ponzi schemes on two popular blockchain platforms: Bitcoin and Ethereum. We list, categorize, and discuss papers that contributed benchmark datasets, developed novel features concerning various aspects of smart Ponzi schemes, and proposed novel machine-learning approaches to detect them.

Jianyu Qu, Li Ruan, Limin Xiao, Liya Hu · 5 authors

As blockchain technology advances at an unprecedented pace, phishing scams increasingly exploit vulnerabilities in Ethereum transactions. These attacks typically involve fraudulent addresses that deceive users and illicitly expropriate digital assets, posing significant threats to the security and integrity of the blockchain ecosystem. In this work, we propose txnet2vec, a novel framework for detecting phishing addresses based on transaction graph analysis. Our approach begins by collecting labeled Ethereum transaction data and constructing a directed, weighted transaction graph, where nodes represent addresses and edges denote transactions. To capture both structural and transactional characteristics, we employ network embedding techniques to learn low-dimensional representations of addresses. To further improve detection accuracy, we design an attention-based feature fusion mechanism that integrates multiple random-walk-based sampling strategies, incorporating transaction amounts, temporal features, and market-driven behaviors. The learned embeddings are then fed into a Support Vector Machine classifier to distinguish phishing from benign addresses. Extensive experimental results demonstrate that txnet2vec achieves superior performance compared to existing baselines in phishing detection within Ethereum’s transaction network.

Nguyen Dang Quynh Nhu, Quan Li, Thai Hung Van, Doan Minh Trung · 5 authors

The burgeoning adoption of economically incentivized smart contracts faces persistent security vulnerabilities, resulting in significant financial losses due to their immutability post-deployment. This paper presents a novel framework integrating fine-tuned large language models (LLMs) with Retrieval-Augmented Generation (RAG) to enhance the precision and explainability of smart contract vulnerability detection. By fine-tuning an open-source LLM and employing RAG, our model dynamically incorporates domain-specific external knowledge during inference, significantly improving threat identification. On two public benchmarks, SolidiFI-Benchmark and Smart Bugs Curated, our fine-tuned Qwen2.5-Coder-14B model (QC-14B-FT) outperforms zero-shot LLMs (GPT-3.5 with and without RAG) in terms of F1-score. Specifically, QC-14B-FT achieves an F1-score of 0.64 on SolidiFI, surpassing GPT-3.5-RAG by 9% and GPT-3.5 by 10%. On Smart Bugs Curated, QC-14B-FT achieves an F1-score of 0.73, outperforming GPT-3.5-RAG by 14% and GPT-3.5 by 19%. These results demonstrate the effectiveness of combining RAG with fine-tuning to provide accurate and clear smart contract security assessments.

Jalees Ahmad -

The global financial ecosystem is currently undergoing an unprecedented digital metamorphosis, characterized by the rapid adoption of decentralized finance, mobile banking, and real-time payment systems. While these advancements have significantly enhanced consumer convenience and operational efficiency, they have simultaneously expanded the attack surface for sophisticated fraudulent actors. Traditional fraud detection methodologies, predominantly reliant on static rule-based frameworks and retrospective manual auditing, are increasingly proving inadequate in the face of modern, high-velocity deceptive maneuvers. This research paper provides an exhaustive analysis of the transition from reactive fraud investigation to proactive, AI-powered real-time prevention. By synthesizing a vast array of peer-reviewed research and industrial case studies, the study explores the implementation of advanced machine learning architectures, including Graph Neural Networks (GNNs) for relational intelligence, Long Short-Term Memory (LSTM) networks for temporal sequence analysis, and Isolation Forests for unsupervised anomaly detection. The analysis further delves into the architectural requirements for real-time processing, highlighting the role of cloud-native microservices, stream-processing engines, and edge intelligence. Furthermore, the paper addresses the critical intersection of technical efficacy, regulatory compliance, and ethical accountability through the lens of Explainable AI (XAI) and Federated Learning. The findings suggest that a multi-layered, synergistic approach - integrating AI with cybersecurity protocol is essential for reducing detection latency from hours to milliseconds, thereby safeguarding the integrity of the global financial network.

Saviz Changizi, Nasibeh Mohammadzadeh, Mohammad Shojafar

This paper presents a first-of-its-kind modular AI framework for telecom fraud detection, integrating machine learning (ML), large language models (LLMs), and blockchain smart contracts to unify statistical classification, semantic reasoning, and decentralized enforcement. A synthetic dataset of 100 users across 300 sessions in Birmingham, UK, simulated telecom usage with$\mathbf{1 \% - 5 \%}$injected fraud, including GPS spoofing, excessive transmission power, and prolonged usage. Seven ML models were trained, with Random Forest optimized using a precision-recall threshold of$\mathbf{0. 7 2 1 7}$. Six configurations varied the decision logic between ML and GPT-4o-based LLMs, with LLMs performing context-aware reasoning via behavioral prompts. Solidity smart contracts on a local Ethereum network enforced decisions, mapping users to blockchain identities with a Proof-of-Stake-style validation mechanism. The ML-only configuration achieved 92.25 % accuracy with perfect user-level precision and recall, while LLM variants enhanced behavioral and temporal reasoning. This framework advances robust and explainable fraud detection for future telecom infrastructures.

Wei Chen, Xinjun Jiang, Tian Lan, Leyuan Liu

No abstract is available for this record.

Jing Huang, Jiahui Li, Honggui Han

Bitcoin money laundering detection faces critical challenges including labeled data scarcity, extreme class imbalance, and transactional heterogeneity. To address these issues, we propose DyHom-SSL, a semisupervised learning framework integrating dynamic pseudolabel optimization, and homophily-aware graph learning. The framework operates in two stages: in the warm-up stage, a similarity-based mechanism dynamically generates thresholds for high-quality pseudolabels, replacing confidence-based selection to enhance flexibility, while in the consistency training stage, a learnable data augmentation module is introduced and optimized through the dual objectives of consistency (semantic preservation) and diversity (feature variation). In addition, homophily distribution leverages topological differences between illicit and licit nodes to resolve class imbalance without distorting data distribution. Extensive evaluations on elliptic, elliptic++, and AMLworld datasets demonstrate state-of-the-art performance, achieving 92.29% precision, 77.30% recall, and 84.02% F1-score on the elliptic dataset. DyHom-SSL outperforms graph and nongraph baselines in both homogeneous and heterogeneous datasets, proving its effectiveness for real-world antimoney laundering (AML) applications.