As Ethereum continues to gain traction as a leading blockchain platform, its open and decentralized nature has also made it an attractive target for fraudulent activities. This paper presents a machine learning-based approach to detect fraudulent Ethereum transactions by analyzing behavioral patterns within transaction data. Using a labeled dataset of Ethereum transactions, various classification algorithms such as Random Forest, XGBoost, and Support Vector Machines were trained and evaluated. The proposed system focuses on identifying anomalies and suspicious transaction behavior by extracting relevant features like gas usage, transaction value, and timing. Experimental results show that the model can achieve high accuracy and precision in distinguishing between legitimate and fraudulent transactions. This work contributes to the growing field of blockchain security by demonstrating the viability of intelligent fraud detection techniques and providing a framework that can be integrated into real-world applications.
Irum Matloob, Shoab Ahmed Khan, Bushra Bashir, Rukaiya Rukaiya · 6 authors
Healthcare recommendations and insurance have recently been one of the most emerging research areas in health informatics. The fraud in health insurance is becoming increasingly common day by day. To handle healthcare insurance fraud, there is an urgent need for an intelligent system that cannot only identify and monitor doctors' and hospitals' behavior regarding the health services they provide to patients but can also recommend doctors and hospitals to insured employees based on the quality of services they provided previously. This system creates patient and doctor profiles separately, based on their rating. The proposed system combines singular value decomposition (SVD), K-nearest neighbors based collaborative filtering (KNN-based CF), item-based collaborative filtering (Item-based CF), content-based filtering using term frequency-inverse document frequency (TF-IDF), and K-means clustering and probability distributions to recommend doctors and insurance plans. The system measures similarity scores between patients and doctors using cosine similarity, which helps to determine similarity scores and refine the recommendations. This study also uses blockchain technology to automate insurance claims reimbursement. The results are validated using real data from the employees of a local hospital. The system provides recommendations with a root mean square error (RMSE) value of 0.478 and a mean absolute error (MAE) value of 0.0422. The insurance plans developed using the proposed system have reduced the overall expenditure of the local hospital, with a reduction in total expenses. Blockchain technology further helps prevent healthcare fraud. In the proposed system, a healthcare insurance claims reimbursement system is built using smart contract technology on the Ethereum blockchain, ensuring security & transparency and lowering the number of healthcare frauds. The system includes roles for the insurance company, healthcare provider, and patients. It also provides a platform for claim submission, approval, or refusal. In Pakistan, no such system existed before recommending doctors from different hospitals based on their professional conduct or the good health services they provide.
The recurring issue of smart contract security breaches has heightened concerns about their reliability and safety, making contract security a critical challenge in the blockchain space. Existing traditional detection techniques predominantly utilize static, expert-defined rule sets, which inherently introduce limitations including reliance on expert knowledge, compromised detection accuracy, and a constrained scope of identifiable vulnerabilities. Therefore, this paper proposes Vul-Sensitive opcode weighting for multi-label smart contract vulnerability detection. The proposed method first processes the source code of smart contracts by converting it to bytecode and then extracts opcodes. Based on a predefined set of critical instructions, Vul-Sensitive opcodes are weighted to enhance the representation of vulnerability-related features. Then, the final feature matrix is utilized by deep learning models for training and classification. To assess the effectiveness of the proposed approach, this paper compares various deep neural network architectures before and after optimization. Experimental results show that it significantly enhances vulnerability detection across all models and consistently outperforms non-weighted methods by effectively strengthening feature representation, achieving the best Micro-F1 score of 90.65%, which validates its effectiveness in multi-vulnerability detection tasks.
This chapter explores the transformative potential of generative artificial intelligence (AI) in combating financial fraud, redefining traditional detection systems. It examines generative AI's capabilities in anomaly detection, behavioral modeling, and predictive analytics, addressing fraud complexities from technologies like cryptocurrencies, decentralized finance (DeFi), and AI-driven scams. The integration of generative AI with blockchain enhances transparency, scalability, and proactive prevention. Real-world case studies highlight its effectiveness against credit card fraud, deepfake impersonations, and synthetic identity fraud. Ethical and operational concerns, including AI bias, privacy, and security, are discussed alongside strategies for ethical governance and collaboration. Generative AI is positioned as a key tool for building resilient and trustworthy financial ecosystems to counter current and emerging fraud threats.
Ahmed Alteneiji, Khaled Shaalan, Suleiman Y. Yerima, Usman Butt
Blockchain networks are decentralized and offer pseudonymity, thus making illegal operations in Bitcoin very difficult to detect and stop. This work reviews recent machine learning approaches designed to spot these activities, focusing on the technical obstacles associated with class imbalance, unlabeled data, and how money laundering methods are rapidly becoming more advanced. Over a decade, reports from 2015 to 2025 were studied to analyze approaches that applied supervised learning, unsupervised clustering, and graph-based neural networks both individually and in mixed hybrid configurations. Important developments in related work are sophisticated blockchain data features, using ensembles to enhance performance, and systems for real-time automatic data processing. Analysis found that models using graph attention achieve over 40% improvement in performance compared to rule-based systems for finding unlawful activity. It further investigates methods for future privacy-preserving analytics, uncovering cross-chain criminals, and making regulations more compatible in the world of decentralized finance, to build better Anti-Money Laundering frameworks.
Shilpa Kottapally, Sr. Software Development Engineer, Adjudication - Rxclaim developement Application, CVS Health, 2100 E lake cook road , Buffalo grove Illinois 60047, USA
International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.
Over the course of more than a decade, blockchain technology has made significant advancements and found applications in various domains. Smart contract, as an integral component of blockchain technology, plays a pivotal role in ensuring the security and robustness of blockchain’s development and diverse applications. Currently, smart contract vulnerabilities have caused millions of dollars in economic losses. Due to the inherent immutability of blockchain technology, once smart contracts are deployed on the blockchain, effecting changes becomes a formidable task. Most of the vulnerability detection tools currently available employ traditional security technologies, which require high expertise and have unsatisfactory detection results. In recent years, deep learning technologies have emerged. Although they do not require extensive expert knowledge, they do require a large amount of labeled data for training. The biggest issue in this field is the lack of a large-scale, accurately annotated public dataset. Hence, we propose a method for detecting smart contract vulnerabilities by leveraging federated learning and BiLSTM, called FASCVD. Our approach not only utilizes federated learning technology to aggregate multiple small datasets while ensuring data privacy but also introduces a bidirectional information extraction technique based on BiLSTM, thereby significantly enhancing the accuracy of vulnerability detection. The experimental results show that our method has already surpassed the best existing methods in terms of accuracy, precision, recall, F1-score, and so on, with an accuracy rate of 95.04%.
C. V. Suresh Babu, M. Bhavesh, J. Janani, C. Mythili Rani
This chapter explores the impact of AI-powered solutions on cybersecurity within the context of cryptocurrency transactions in e-commerce. The primary objective is to investigate how AI can mitigate the growing cybersecurity risks associated with cryptocurrency fraud, enhancing the safety of e-commerce platforms. Targeting researchers, AI engineers, and e-commerce professionals, this study employs a mixed-method approach, combining case studies, expert interviews, and comparative analysis of AI-based tools and traditional security systems. The findings highlight the significant potential of AI, particularly in predictive analytics and real-time fraud detection, to combat cryptocurrency-related cybercrimes. The chapter also addresses the challenges of integrating AI with existing e-commerce frameworks and discusses ethical concerns related to privacy and surveillance. The conclusion emphasizes the need for further research into real-time AI solutions and the development of international regulatory standards for AI in cryptocurrency security.
The rapid evolution of financial fraud in digital finance applications—such as mobile banking, cryptocurrency transactions, and online payment gateways—has rendered traditional rule-based detection systems increasingly ineffective, leading to heightened financial losses and security vulnerabilities. These systems struggle to adapt to complex fraudulent schemes, resulting in inefficiencies in identifying such activities. This research introduces a Scalable Black Widow-driven Gradient Boosting Machine (SBW-GBM) framework designed to enhance fraud detection through real-time data analysis and machine learning (ML). The framework evaluates performance in both decentralized finance and traditional financial contexts, utilizing two separate datasets. The first dataset is based on an Ethereum Phishing Transaction Network; the second originates from Kaggle and pertains to Credit Risk Assessment. Data preparation involves addressing missing values, normalizing numerical features, and employing outlier detection techniques to improve data quality. For feature extraction, Principal Component Analysis (PCA) reduces data dimensionality while preserving critical information regarding transaction behaviors. The classification employs Gradient Boosting Machine (GBM) for high predictive accuracy, with the SBW algorithm dynamically fine-tuning GBM hyperparameters to enhance efficiency. Inspired by black widow spiders, the SBW algorithm optimizes hyperparameter selection by eliminating weak solutions and reinforcing stronger ones. This results in an adaptive fraud detection model trained on labeled transaction data. Experimental results confirm that SBW-GBM achieves an F1-score of 0.899, an accuracy of 0.948, an error rate of 0.128, and an experimental runtime of 0.40 seconds on Dataset 1, outperforming the baseline FFSVM. For Dataset 2, SBW-GBM attains a precision of 0.875, a recall of 0.660, an F1-score of 0.750, and an AUC of 0.932, surpassing benchmark traditional classifiers. By continuously learning from new transaction patterns, the proposed framework ensures adaptability to emerging threats and supports real-time fraud detection.
Due to the immutable nature of blockchain, vulnerability detection in on-chain smart contracts is imperative to ensure the security of blockchain transaction. As smart contracts automate significant financial and operational transactions, detecting vulnerabilities before they are exploited is critical. Recently, the application of machine learning techniques to this domain has increased, primarily due to their powerful feature extraction capabilities and operational efficiency in detecting anomalies. Considerable efforts in past research have focused on mining semantic and syntactic features from off-chain source code of smart contracts, typically written in high-level languages like Solidity. However, on-chain smart contracts, which are represented in the form of opcodes, lack these high-level semantic features. This absence necessitates different approaches for effective vulnerability detection. Although on-chain smart contracts lack high-level semantic features, the limited number of characters in opcodes results in more distinct frequency patterns of code. Therefore, in this paper, we explore a multi-class vulnerability detection approach based on the frequency features of smart contract opcodes. This paper provides a simple yet effective feature embedding method for on-chain opcode contract. Experiments on both binary and multi-class vulnerability detection tasks have been conducted to validate its scalability and effectiveness.
We introduce a hybrid system for detecting suspicious blockchain transactions, blending explainable machine learning (like Random Forest) with neural networks to analyze both raw transaction details and network patterns. Our approach achieves industry-leading accuracy (92% F1-score), solving two critical flaws in existing tools: 1) It cuts redundant data noise by 64% using smart feature filtering, and 2) uncovers hidden money trails through transaction graph analysis. While effective, current limitations include reliance on historical data—making it vulnerable to evolving scams like manipulated transaction networks in DeFi schemes—and slower processing times (32 training cycles) that challenge real-time monitoring on high-speed networks like Ethereum. Planned upgrades include dynamic AI models that adapt to live transaction flows and efficient detection systems for time-sensitive environments. We’re also developing stress tests using simulated cyberattack patterns and privacy-focused collaborative training across blockchain nodes. By merging technical precision with clear audit trails, this framework helps financial investigators spot risks like dark market ties while meeting strict compliance standards, offering a practical solution to balance speed and detection accuracy in crypto markets.
B. Rohith, N.R. Sathis Kumar, P. Animma Srinivasine, Balram Babu · 5 authors
Modern online finance operations create difficult obstacles for detecting fraudulent activity. While deep learning (DL) models effectively identify fraudulent activities, their "black-box" nature raises concerns about trust and interpretability. The research design recommends an XDL-Blockchain solution for fraud detection that enhances transparency and accuracy alongside enhanced security capabilities. SHAP and Grad-CAM methods supply interpretation features that enhance stakeholder confidence and blockchain technologies deliver permanent decentralized identity proofing systems which minimize fraudulent activity. Experimental assessments using genuine financial data show that the proposed model delivers superior outcomes compared to conventional detection systems regarding precision and network security. The framework unites artificial intelligence with blockchain technology to provide banks with a dependable system that delivers reliable detection of contemporary financial fraud.
The proliferation of FinTech platforms has transformed global financial systems by offering innovative, real-time services.However, this evolution has also expanded the surface area for cyber-enabled financial fraud, especially across multi-layered infrastructures comprising mobile banking apps, decentralized finance (DeFi) platforms, digital wallets, and cloud-based services.Traditional machine learning and rule-based systems have demonstrated limited adaptability in detecting increasingly sophisticated attack vectors that span multiple digital layers.This paper presents a comprehensive exploration of explainable deep learning (XDL) models tailored to detect complex cyber-enabled fraud schemes across interconnected FinTech ecosystems.The study begins with an overview of the structural and technological evolution of FinTech infrastructure, followed by an examination of the most prevalent and emerging fraud typologies including synthetic identity fraud, account takeover, transaction laundering, and insider collusion.Emphasis is placed on the limitations of black-box AI models in high-stakes financial environments where interpretability is critical for regulatory compliance, stakeholder trust, and legal recourse.We introduce an explainable deep learning framework incorporating convolutional neural networks (CNNs) for behavioral biometrics, graph neural networks (GNNs) for multi-entity relationship mapping, and attention-based mechanisms for anomaly prioritization.The model integrates SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to improve transparency without compromising predictive performance.Evaluation is conducted using real-world transaction data from anonymized FinTech institutions, with metrics highlighting accuracy, false positive reduction, and interpretability scores.The paper concludes by discussing policy implications, ethical considerations, and future research directions in explainable AI for secure financial innovation.
K. Praveen Kumar, Shaik Lubna, Pullagurla Tharun Kumar
The decentralized nature of Ethereum exposes it to phishing, Ponzi schemes, and money laundering. Traditional fraud detection methods fail to identify complex patterns in transactions. This paper proposes a deep learning model based on Bi-Directional Long Short-Term Memory (Bi-LSTM) and Attention Mechanism for enhancing fraud detection accuracy in Ethereum transactions. The model handles sequential transaction data and employs Bi-LSTM to learn temporal correlations and Attention to select appropriate features. On a Kaggle Ethereum dataset, the model achieved 97% accuracy, 97% precision, 97% recall, and a 97% F1-score, much higher than existing works. The study demonstrates the usefulness of deep learning for the security of blockchain systems, having a robust process for realtime fraud detection.
The prosperity of Ethereum has led to a rise in phishing scams. Initially, scammers lured users into transferring or granting tokens to Externally Owned Accounts (EOAs). Now, they have shifted to deploying phishing contracts to deceive users. Specifically, scammers trick victims into either directly transferring tokens to phishing contracts or granting these contracts control over their tokens. Our research reveals that phishing contracts have resulted in significant financial losses for users. While several studies have explored cybercrime on Ethereum, to the best of our knowledge, the understanding of phishing contracts is still limited. In this paper, we present the first empirical study of phishing contracts on Ethereum. We first build a sample dataset including 790 reported phishing contracts, based on which we uncover the key features of phishing contracts. Then, we propose to collect phishing contracts by identifying suspicious functions from the bytecode and simulating transactions. With this method, we have built the first large-scale phishing contract dataset on Ethereum, comprising 37,654 phishing contracts deployed between December 29, 2022 and January 1, 2025. Based on the above dataset, we collect phishing transactions and then conduct the measurement from the perspectives of victim accounts, phishing contracts, and deployer accounts. Alarmingly, these phishing contracts have launched 211,319 phishing transactions, leading to 190.7 million in losses for 171,984 victim accounts. Moreover, we identify a large-scale phishing group deploying 85.7% of all phishing contracts, and it remains active at present. Our work aims to serve as a valuable reference in combating phishing contracts and protecting users' assets.
Sheng Zhang, Tan Kia Quang, Shen Wang, Shengchen Duan · 6 authors
Scam contracts on Ethereum have rapidly evolved alongside the rise of DeFi and NFT ecosystems, utilizing increasingly complex code obfuscation techniques to avoid early detection. This paper systematically investigates how obfuscation amplifies the financial risks of fraudulent contracts and undermines existing auditing tools. We propose a transfer-centric obfuscation taxonomy, distilling seven key features, and introduce ObfProbe, a framework that performs bytecode-level smart contract analysis to uncover obfuscation techniques and quantify obfuscation complexity via Z-score ranking. In a large-scale study of 1.03 million Ethereum contracts, we isolate over 3 000 highly obfuscated contracts and identify two scam archetypes, three high-risk contract categories, and MEV bots that employ a variety of obfuscation maneuvers such as inline assembly, dead code insertion, and deep function splitting. We further show that obfuscation substantially increases both the scale of financial damage and the time until detection. Finally, we evaluate SourceP, a state-of-the-art Ponzi detection tool, on obfuscated versus non-obfuscated samples and observe its accuracy drop from approximately 80 percent to approximately 12 percent in real-world scenarios. These findings highlight the urgent need for enhanced anti-obfuscation analysis techniques and broader community collaboration to stem the proliferation of scam contracts in the expanding DeFi ecosystem.
Abstract— This study integrates blockchain technology and machine learning to enhance credit card fraud detection. ​ Precise fraud prediction is performed using advanced algorithms such as Random Forest, Logistic Regression, XGBoost, and Bayesian models. ​ Tools such as Ganache and MetaMask from Ethereum blockchain facilitate safe and transparent tracking of suspicious transactions. ​ Decentralized and tamper-proof properties of blockchain add reliability, and machine learning adds precision and flexibility. The system is highly accurate and transparent and has the potential to be used to fight financial fraud. ​ Keywords— Credit Card Fraud, Blockchain, Machine Learning, Ethereum, Web3, SMOTE, XGBoost, Streamlit
Decentralized Finance (DeFi) has revolutionized financial transactions by enabling open, permissionless access to financial services. However, its lack of centralized oversight and pseudonymous architecture have also brought by fraudulent activities. This study presents a novel framework for fraud detection in DeFi that integrates graph neural networks (GNNs) with multi-agent reinforcement learning (MARL). Leveraging a directed transaction graph comprising 50,000 Ethereum addresses and over 120,000 token transfers, this paper evaluates four detection pipelines: extreme gradient-boosted decision trees (XGBoost), a GNN-only model (GCN), a standalone reinforcement learning agent (PPO), and a proposed GNN+RL hybrid model. The hybrid system combines graph-based embeddings with adversarial policy learning, where a fraudster and a detector co-evolve through a multi-agent PPO setup using PettingZoo’s ParallelEnv. Synthetic fraud strategies are generated using a GAN and projected into the GCN embedding space to simulate adaptive threats. Experimental results show that while GCNs outperform flat-feature models, the GNN+RL hybrid achieves superior balance across accuracy (84.58%), AUC (0.8176), and F1 score (0.7493), capturing both structural and behavioral fraud signals. Reward convergence curves further illustrate emergent adversarial dynamics. The proposed framework demonstrates the effectiveness of combining relational inductive biases, dynamic decision-making, and adversarial augmentation for resilient fraud detection. Future work includes extending to cross-chain analytics and enriching contextual understanding through integration with large language models.
Smart contract classification holds significant application value in the field of blockchain. However, existing methods suffer from inefficiencies and high computational complexity when dealing with smart contract data. To address these issues, this paper proposes a Cluster-BERT model based on neural clustering techniques. The model reduces the computational burden of self-attention mechanisms by clustering attention heads, thereby improving training efficiency. The Cluster-BERT model comprises multiple modules. Module 1 preprocesses smart contract data, converting abstract syntax trees and graph structure features into text representations suitable for BERT models. Module 2 serves as the core of the model, introducing neural clustering methods to reduce computational complexity. Module 3 further optimizes the model by finding the optimal number of centroids, achieving a balance between training efficiency and classification accuracy. Experimental results show that our proposed Cluster-BERT achieved an accuracy of 91.42%, a recall of 91.44%, and an F1 score of 91.43%, which indicates a noticeable improvement over the baseline model. Our model reduces computational complexity from quadratic to linear, resulting in an average reduction of 8.48% in training time and 7.88% in prediction time compared to the baseline model. On the smart contract dataset, the accuracy and precision of our model outperformed other models proposed in recent years by 1% to 2% points on average.
Minh Tri Le, O. M. Harris, Charlotte Bennett, Fiona Greene
With the deep penetration of blockchain technology across various fields, its security system faces severe challenges, and fraudulent activities are becoming increasingly frequent. This study focuses on the problem of fraud detection in blockchain and proposes an innovative model, FraudGNN, based on Graph Neural Networks (GNN). The model constructs a dynamic transaction graph, where transaction addresses are treated as nodes and asset transfer relationships as edges, incorporating time-series features. A Graph Attention Network (GAT) is used to extract behavioral features from node neighborhoods. In addition, a Bidirectional Long Short-Term Memory network (Bi-LSTM) is introduced to capture behavioral paths across block-level transactions, enabling accurate classification and prediction of abnormal accounts within blockchain networks. Experiments conducted on an Ethereum transaction dataset—containing approximately 3.6 million transaction records and 40,000 labeled addresses—show that the FraudGNN model significantly outperforms traditional methods such as Random Forest and Graph Convolutional Networks (GCN) in key metrics, achieving 91.2% precision, 87.5% recall, and an F1-score of 89.3%. In particular, the model demonstrates stronger generalization and reasoning capabilities when identifying previously unseen addresses, offering solid technical support for improving blockchain security systems.
In the rapidly evolving landscape of digital finance, the increasing sophistication of fraudulent activities has created significant challenges for traditional detection systems. This research paper investigates the integration of federated learning with unsupervised deep learning techniques to meet the dual demands of data privacy and robust fraud detection. Using two real-world datasets, the Credit Card Fraud dataset and the NeurIPS 2022 Bank Account Fraud dataset, we developed a federated framework based on deep autoencoders. The framework simulates decentralized model training across multiple financial nodes while ensuring that raw data remains local. The methodology includes detailed data pre-processing steps, the construction of a compact autoencoder architecture and a threshold-based approach to anomaly detection. Experimental outcomes demonstrate the model’s ability to distinguish between legitimate and fraudulent transactions by the use of performance evaluation through the use of Receiver Operating Characteristic (ROC) curves, confusion matrices, and reconstruction error distributions. Despite the challenges of class imbalance and data heterogeneity, the proposed model achieved promising results by maintaining competitive discrimination capabilities. Overall, the research study establishes the potential of federated learning combined with anomaly detection to provide scalability, privacy preservation, and interpretable fraud detection solutions suitable for real-world financial environments.