Marlena Broniszewska, Wiktor B. Daszczuk, Denny B. Czejdo
Global digitalization has accelerated, leading to continuous online shopping and services growth. However, the centralized nature of traditional e-commerce platforms raises concerns about data control, privacy, and potential single points of failure. Blockchain technology offers a decentralized alternative that addresses these issues, improving online transactions with enhanced privacy and anonymity for users. This article explores the problem of anonymization in web services by developing an anonymous online auction system using blockchain and zero-knowledge proof (ZKP). We propose a solution that employs ZKP in two stages: first, to verify that a user is eligible to participate in the auction, thereby creating a list of potential bidders; second, to prove that a bid is placed by a user from this list without disclosing their identity. This approach allows participants to engage in auctions anonymously, protecting their interests from competitors and sellers. The system eliminates the need for a trusted third party by leveraging the blockchain immutable ledger for transparency, giving users full control over their data and participation. We present the architecture and implementation details of the system, demonstrating its feasibility and potential to enhance privacy and security in online auctions.
Muhammad Shoaib Farooq, Shahzada Fahad Munir, Muhammad Faraz Manzoor, Momina Shaheen
The increasing complexity of fraudulent activities requires advanced fraud detection systems, as existing solutions lack effectiveness due to two challenges. First, privacy concerns prevent financial institutions from sharing sensitive transaction data. Second, data imbalance causes biased models, as fraudulent transactions represent a small fraction of total transactions, leading to poor fraud detection performance. To address these challenges, we propose an AI‐driven adaptive federated learning (AFL) framework for credit card fraud detection (CCFD). AFL enables decentralized learning, allowing financial institutions to train a global fraud detection model collaboratively without sharing raw transaction data. The model aggregation is performance‐adaptive, weighting client contributions based on detection accuracy to ensure a robust global model. To overcome data imbalance, we introduce a multistep data balancing framework integrating Tomek links for undersampling, borderline‐SMOTE for oversampling, and cognitive sample pruning to remove misleading samples. To evaluate the robustness and generalizability of the proposed framework, we conducted experiments on both the widely used 2013 Kaggle dataset and the Sparkov simulated dataset (2019‐2020). The Sparkov dataset, which contains interpretable demographic and merchant‐level features, allowed us to test the model’s adaptability to diverse data sources. The results demonstrate that the proposed AFL framework, combined with advanced data balancing, significantly outperforms traditional models, achieving 99% accuracy, 99.5% precision, 99.4% recall, and 99% F1‐score on the Kaggle dataset, and 97.4% accuracy, 99.5% precision, 97.5% recall, and 98.4% F1‐score on the Sparkov dataset. This research highlights AI’s transformative role in finance, particularly in enhancing fraud detection systems with improved accuracy, robustness, security, and scalability.
Fraud risks are on the rise with the increase in cryptocurrency transactions; the traditional detection methods become inadequate. This paper proposes a hybrid deep-learning framework for real-time fraud detection in Bitcoin transactions. Algorithms like Random Forest, support vector machine (SVM), Logistic Regression, and XGBoost are used to analyse transaction patterns and anomalies with a high level of accuracy. Different models have been tested in transaction data for Bitcoin, and the best-performing model was XGBoost with an accuracy of 96.94%. Advanced machine learning techniques enrich a system through secure data-driven insights and real-time anomaly detection, thus enhancing fraud risk detection. The obstacles faced are scalability, privacy issues, and inability to adjust models according to the evolving fraud technique. Future advancements might deal with federated learning, encryption methods, and cross-platform prevention to make the detection of fraud more secure. This paper indicates how well deep learning-based detection of fraud can scale and work efficiently to strengthen trust in digital financial systems.
Illicit transaction detection on blockchain networks presents a critical challenge due to the pseudonymous, decentralized, and high-volume nature of decentralized finance (DeFi) ecosystems. Traditional machine learning models struggle to effectively capture the temporal dynamics and irregular patterns of illicit behavior, while graph-based methods often incur high computational costs and rely on static relational structures. In this paper, we propose a novel dual-attention framework—GAM-CoT Transformer—for robust transaction-level anomaly detection. The proposed model integrates two key components: a Global Attention Module (GAM) that adaptively reweights feature channels and temporal steps to emphasize salient patterns, and a Contextual Transformer (CoT) block that efficiently models short-range dependencies using grouped convolutions instead of full self-attention. This design enables the model to simultaneously achieve computational efficiency, temporal expressiveness, and improved detection sensitivity. We evaluate our approach on a real-world blockchain transaction dataset and demonstrate its superiority over conventional classifiers including Random Forest, XGBoost, and LSTM-based models. The GAM-CoT Transformer achieves higher recall and F1 scores, particularly for the minority illicit class, while maintaining fast convergence and deployment scalability. Our method offers a practical and effective solution for enhancing the security of blockchain systems through intelligent transaction behavior modeling.
Vulnerability detection is particularly relevant in smart contracts, where modifying the code after deployment is impossible. Machine learning solutions provide greater efficiency than static analyzers in speed and detection. This study evaluates various classic machine-learning techniques and state-of-the-art neural networks for training a vulnerability detector. We analyze the largest and most reliably labelled dataset of smart contracts currently available, experimenting with six data representations of smart contracts and a multimodal approach. Our experiments show that both deep and traditional machine learning methods excel in different scenarios. Notably, eXtreme Gradient Boosting achieved an F1-score of 0.91 with the multimodal approach, which suggests its potential for more robust classification. At the same time, the results underscore the need for larger datasets to showcase the full potential of the evaluated methods.
As decentralized finance (DeFi) expands, Ethereum’s role as the backbone for digital asset exchange, smart contracts, and financial protocols has grown—but so has its exposure to fraud. Phishing, money laundering, and malicious contracts exploit its openness. Existing ML and deep learning models often lack the balance between speed, accuracy, and explainability needed for real-time blockchain analysis. High-performing models like transformers are accurate but too resource-heavy and opaque. This study leverages TabNet—a sparse-attention deep learning model optimized for tabular Ethereum transaction data. It dynamically selects relevant features during training, enhancing both interpretability and efficiency. With an accuracy of 0.86, precision of 0.80, and F1-score of 0.79, TabNet outperforms traditional models in fraud detection while remaining lightweight and transparent. Its feature-level insights make it ideal for environments where trust, latency, and transparency are crucial. The results position TabNet as a scalable, practical alternative for fraud detection in blockchain ecosystems.
Bitcoin is a decentralized cryptocurrency, which is rapidly growing and offering many advantages. Although its structure protects users from some types of fraud, it is not completely immune, while fraud detection in Bitcoin remains still relatively unexplored. In this paper, we use a graph to model Bitcoin transactions and benefit from the graph’s structure to overcome the lack of informative transaction and user data. We utilize network analysis for feature extraction and model fraud detection as a classification problem using a Deep Neural Network as our classifier. Furthermore, we propose a novel approach that combines a Variational Graph Autoencoder (VGAE), for deriving appropriate node and graph embeddings, and supervised learning to detect fraudulent Bitcoin transactions. Our experimental results show that the proposed approach, while also affected by high class imbalance, similarly to using only the graph-based features for classification, performs significantly better in detecting high-risk areas in the graph.
Edward Danso Ansong, Simon Bonsu Osei, Raphael Adjetey Adjei
The surge in identity fraud, driven by the rapid adoption of mobile money, internet banking, and e-services during the COVID-19 pandemic, underscores the need for robust cybersecurity solutions. Zero-Knowledge Proofs (ZKPs) e... | Find, read and cite all the research you need on Tech Science Press
Blockchain's decentralized characteristics have posed unique challenges and unlocked novel opportunities for the accounting and auditing sector. While the potential impact of blockchain and smart contracts on auditing has been raised, comprehensive studies remain scarce. Using the Solidity language, this study explores the viability of encoding into smart contracts specific auditing rules that can automatically identify suspicious transactions in common fraud schemes. To illustrate the feasibility, it presents a proof-of-concept framework encompassing system architecture, smart contract development, and workflow procedures. Simulation results demonstrate that blockchain-based smart contract approach in this study can effectively identify problematic transactions in near real-time. Consequently, this could help auditors to allocate audit resources to focus efforts on higher risk transactions. The findings provide implications for future studies on the application of smart contracts in auditing.
Fraud detection in blockchain networks presents unique challenges due to the decentralized and<br/>pseudonymous nature of transactions. This study introduces a novel Multilayer Topology-Aware Graph<br/>Contrastive Learning (MTGCL) framework to detect fraudulent activity within the Ethereum transaction<br/>network. The proposed approach leverages node-level and topology-level representations, integrating<br/>persistent homology to capture high-order structural patterns and enhance anomaly detection. By<br/>employing adaptive graph augmentation and self-supervised contrastive learning, MTGCL effectively<br/>improves fraud detection performance. Empirical evaluations demonstrate that MTGCL outperforms<br/>existing graph contrastive learning models in classification accuracy across multiple time periods while<br/>maintaining competitive computational efficiency. The framework also exhibits scalability for large-scale<br/>blockchain analysis, achieving lower computational costs compared with other baselines methods. These<br/>findings highlight MTGCL’s potential for real-world applications, offering valuable insights for financial<br/>institutions, cryptocurrency exchanges, regulatory bodies, and blockchain analytics firms in combating<br/>fraudulent activities and enhancing anti-money laundering compliance.
Teng Huang, Jiahui Huang, Changyu Dong, Sisi Duan · 5 authors
The pseudonymity nature of Ethereum provides a protective umbrella for criminal activities, allowing criminals to develop a series of black industries such as phishing scams in unregulated areas. In order to exploit the relational inductive bias to discover the real identity of anonymous accounts, graph neural networks (GNNs) have been widely used in Ethereum fraud detection tasks as an effective and powerful framework. However, the expressive power of GNN’s 1-hop message passing mechanism is bounded by the Weisfeiler-Leman (1-WL) test, degrading the fraud detection performance on the Ethereum network. This paper proposes a structure-aware Mamba framework, named SAMamba. Specifically, SAMamba uses a subgraph encoding strategy to capture complex structural patterns and introduces Mamba’s exceptional sequence modeling capabilities to route global information. In order to filter task-relevant information from dense information, the attention mechanism and the selection mechanism are introduced from local and global perspectives, respectively. These tailor-made designs enable SAMamba to distinguish subtle differences in structural patterns and selectively aggregate task-oriented information, thereby demonstrating exceptional performance in fraud detection tasks. Extensive experiments on real-world Ethereum data demonstrate that SAMamba outperforms state-of-the-art methods. The codes are publicly available on Github: https://github.com/deepang-ai/SAMamba.
Amir M. Ebrahimi, Bram Adams, Gustavo A. Oliva, Ahmed E. Hassan
Software applications that run on a blockchain platform are known as DApps. DApps are built using smart contracts, which are immutable after deployment. Just like any real-world software system, DApps need to receive new features and bug fixes over time in order to remain useful and secure. However, Ethereum lacks native solutions for post-deployment smart contract maintenance, requiring developers to devise their own methods. A popular method is known as the upgradeability proxy contract (UPC), which involves implementing the proxy design pattern (as defined by the Gang of Four). In this method, client calls first hit a proxy contract, which then delegates calls to a certain implementation contract. Most importantly, the proxy contract can be reconfigured during runtime to delegate calls to another implementation contract, effectively enabling application upgrades. For researchers, the accurate detection of UPCs is a strong requirement in the understanding of how exactly real-world DApps are maintained over time. For practitioners, the accurate detection of UPCs is crucial for providing application behavior transparency and enabling auditing. In this paper, we introduce UPC Sentinel, a novel three-layer algorithm that utilizes both static and dynamic analysis of smart contract bytecode to accurately detect active UPCs. We evaluated UPC Sentinel using two distinct ground truth datasets. In the first dataset, our method demonstrated a near-perfect accuracy of 99%. The evaluation on the second dataset further established our method's efficacy, showing a perfect precision rate of 100% and a near-perfect recall of 99.3%, outperforming the state of the art. Finally, we discuss the potential value of UPC Sentinel in advancing future research efforts.