The main goal of this research is to examine how well blockchain technology functions to prevent financial fraud. The purpose of this study is to determine whether blockchain technology can effectively combat financial fraud, a type of white-collar crime that is dramatically increasing throughout the world. With this concern, this project aimed to identify the effectiveness of blockchain technology in preventing financial fraud among public listed companies in Malaysia. Since there are only a few studies have analysed various factors that influence financial fraud, this study intends to achieve the aim of the study which is to figure out the level of influence that the factors identified as independent variables on the dependent variable, financial fraud. The primary method is used by the researcher to acquire the data. The three factors examined in this study—immutability, consensus method, and distributed ledger technology—all have a major impact on financial fraud. The data was acquired from staff of public listed companies in Malaysia. Statistical Package of the Social Sciences (SPSS) is used to analyze the correlations between the three factors and all of the factors were shown to have a substantial link with financial fraud in Malaysian public listed companies. This study's findings suggest that individuals and businesses should be aware of the threats of financial theft that exist all around them and the value of having key tools that are resistant to phishing scams. The investigation raises awareness of the application of blockchain technology among customers as well as companies to prevent financial fraud.
Bitcoin has become a popular method for illegal transactions, such as ransomware payments and money laundering. Detecting these activities within the Bitcoin blockchain is challenging due to the lack of transaction labels and the network's enormous size, allowing bad actors to hide their actions. Previous studies have suggested using unsupervised anomaly detection or supervised and active learning techniques for identifying illicit activity within Bitcoin's network. This paper presents a novel machine-learning methodology that combines feature engineering with supervised learning algorithms to identify illicit transactions in the Bitcoin network. The approach shows promising results in accurately classifying transactions as illicit or legitimate. This method not only provides an efficient solution for detecting unauthorized transactions but also holds significant implications for establishing robust regulatory frameworks for digital currencies.
Nov 1, 2023·2023 International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE)
Numerous cutting-edge commercial possibilities have emerged as a result of the widespread use of cryptocurrencies, but it has also drawn a growing number of fraudulent individuals looking to commit fraud. This paper proposes an extensive strategy that makes use of machine learning(ML) techniques to meet the urgent demand for effective fraud detection tools inside the cryptocurrency industry. This paper presents a comprehensive investigation of several fraudulent practices that are common in the virtual currencies ecosystem. The next step has been to investigate several of ML approaches, including Adaptive Boosting(AdaBoost), Random Forest(RF) and Extreme Gradient Boosting(XGBoost), that are designed to spot unusual patterns suggestive of fraudulent behaviour. A crypto fraud detection dataset of fraud instances and real-world cryptocurrency transactions has been utilised in trials to gauge the effectiveness of the suggested approach. To gauge the accuracy and resilience of the models, performance metrics including precision, recall, and F1-score are used. In order to establish which algorithms are most suited for real-time fraud detection, multiple approaches have also been examined for efficiency and scalability. The results show how ML techniques can be used to improve the security of cryptocurrency networks. The XGBoost approach has the best accuracy, at 98%, followed by AdaBoost and RF, at 67% and 90% respectively. The suggested models show encouraging results in spotting fraudulent behaviour, with substantial successes in spotting previously unidentified attack patterns.
Helen Milner, Redowan Mahmud, Mahbuba Afrin, Sashowta G. Siddhartha · 6 authors
The popularity of Ethereum as a platform for Stablecoin transactions (for example, AUDN) continues to rise. It is therefore paramount that the integrity and security of transactions within these decentralized systems are guaranteed. The intricate network of interactions occurring during the exchange of cryptocurrencies made the task of identifying specific transactions as fraudulent difficult because fraudulent behaviour can be concealed within legitimate smart contract operations. Leveraging the inherent structure and interconnectedness of Ethereum transactions, this paper proposes a comprehensive framework to address issues such as Frontrunning within the cryptocurrency ecosystem. Constructing a knowledge graph representation of fraudulent Ethereum blockchain transactions, the proposed solution captures the relationships between addresses, transactions, and smart contracts and generates BotVictim recommendations based on Victim Receiver similarity scores exceeding 85%. These results are generated by excluding temporal transactions, a unique approach when examining the Ethereum network. Thus, our approach enables early detection and prevention of fraudulent activities, potentially safeguarding the interests of cryptocurrency users and mitigating potential financial losses. To evaluate the effectiveness of the proposed framework, its performance is compared against traditional fraud detection methods. The proposed solution demonstrates superiority in terms of accuracy and efficiency.
The emergence of the Bitcoin cryptocurrency marked a new era of illegal transactions. Cryptocurrency provides some level of anonymity allowing its users to create an unlimited number of wallets with alias addresses, which makes it challenging to identify the actual user. This is used by criminals for the purpose of making illegal transactions. At the same time, Bitcoin stores and provides information about all committed transactions, which opens up opportunities for identifying suspicious behavior patterns in this network using data mining. The problem of detecting suspicious activity in the Bitcoin network can be solved with sufficiently high accuracy using machine learning methods. The paper provides a comparative study of various machine learning methods to solve the mentioned problem: logistic regression, decision tree, random forest, gradient boosting.. Selecting hyper parameters, rebalancing the dataset, and active learning are particularly important. The most important hyperparameters of the algorithms are described. Metrics show that the gradient boosting looks the most promising. In total 38 features of bitcoin addresses were identified. The top features are presented in the paper.
Abstract Security threats posed by Ponzi schemes present a considerably higher risk compared to many other online crimes. These fraudulent online businesses, including Ponzi schemes, have witnessed rapid growth and emerged as major threats in societies like Nigeria, particularly due to the high poverty rate. Many individuals have fallen victim to these scams, resulting in significant financial losses. Despite efforts to detect Ponzi schemes using various methods, including machine learning (ML), current techniques still face challenges, such as deficient datasets, reliance on transaction records, and limited accuracy. To address the negative impact of Ponzi schemes, this paper proposes a novel approach focusing on detecting Ponzi schemes on Ethereum using ML algorithms like random forest (RF), neural network (NN), and K-nearest neighbor (KNN). Over 20,000 datasets related to Ethereum transaction networks were gathered from Kaggle and preprocessed for training the ML models. After evaluating and comparing the three models, RF demonstrated the best performance with an accuracy of 0.94, a class-score of 0.8833, and an overall-score of 0.96667. Comparative evaluations with previous models indicate that our model achieves high accuracy. Moreover, this innovative work successfully detects key fraud features within the Ponzi scheme dataset, reducing the number of features from 70 to only 10 while maintaining a high level of accuracy. The main strength of this proposed method lies in its ability to detect clever Ponzi schemes from their inception, offering valuable insights to combat these financial threats effectively.
The phishing scams pose a serious threat to the ecosystem of Ethereum which is one of the largest blockchains in the world. Such a type of cyberattack recently has caused losses of millions of dollars. In this paper, we propose a Self-supervised IncrEmental deep Graph lEarning (SIEGE) model, for the phishing scam detection problem on Ethereum. To overcome the data scalability challenge, we propose splitting the original Ethereum transaction data and constructing transaction graphs for each split. Confronted with the minimal labeled data available, we resort to graph-based self-supervised learning. We design a spatial pretext task to learn high-quality node embeddings inside a single graph split, as well as an incremental learning paradigm and a temporal pretext task to facilitate information flow between different graph splits. To evaluate the effectiveness of SIEGE, we gather a real-world dataset consisting of six-month Ethereum transaction records. The results demonstrate that our model consistently outperforms baseline approaches in both transductive and inductive settings.
Hanbiao Du, Zheng Che, Meng Shen, Liehuang Zhu · 5 authors
With the property of helping users further enhance the anonymity of transactions, mixing services in blockchain have gained wide popularity in recent years. However, the strong untraceability offered by mixing services has led to the abuse of them by criminals for money laundering and committing fraud. These illegal actions pose significant threats to the blockchain ecosystem and financial order. In this paper, we focus on the problem of correlating the addresses of mixing transactions in Tornado Cash, a widely-used mixing service on Ethereum. We propose a graph neural network framework named MixBroker, which aims to break the anonymity of Tornado Cash by correlate mixing addresses from the perspective of node-pair link prediction. Specifically, we construct a Mixing Interaction Graph (MIG) using raw Ethereum mixing transaction data that can be used for subsequent analysis. To better represent the properties of mixing account nodes, we extract features from account nodes in the MIG from multiple perspectives. Furthermore, we design a GNN-based link prediction mechanism to serve as the backbone of MixBroker. This mechanism captures the interconnected nature of nodes within the MIG and calculates the probability of correlation between account nodes through node embeddings. In addition, to solve the problem of lacking ground-truth, we collect a large number of real mixing transactions of Ethereum in Tornado Cash and construct a ground-truth dataset by combining the principles of Ethereum Name Service (ENS). We conduct extensive experiments on the datasets, and the results demonstrate that MixBroker has a superior performance over other state-of-the-art methods on the address correlation problem in Ethereum mixing transactions.
Due to the decentralized and transparent characteristics of the blockchain ecosystem, malicious activities such as phishing scams on the Ethereum platform result in significant financial losses for users. The current methods for detecting phishing largely rely on analyzing original transactions, which makes uncovering hidden transaction patterns challenging. To tackle this limitation, we introduce the Spatio-Temporal Fusion Network (STFN) designed to identify phishing scams on the Ethereum network. Specifically, STFN incorporates two key components: the transactions subgraph encoder for formalizing spatial features, and the transaction sequence BERT encoder for capturing temporal features. By fusing these spatio-temporal features, we facilitate their integration into a machine learning algorithm for classifying phishing accounts. The experimental outcomes underscore the effectiveness of the STFN, achieving an AUC of 93.26% and a Recall of 94.53%, outperforming previous methods for Ethereum phishing detection.
Cryptocurrencies, particularly Bitcoin, have gained considerable attention due to their decentralized nature and potential for high returns. However, they are also subject to fraud-ulent activities, posing challenges to security and transparency. In this paper, we aim to detect fraudulent Bitcoin transactions using machine learning models, including traditional models like Logistic Regression, Decision Trees, and Random Forests, in addition to other deep learning models. Our results demonstrate that when trained on the complete transactional dataset, the Random Forest model outperforms other models, suggesting its potential for effectively detecting fraudulent transactions within the Bitcoin network.
The Ponzi scheme implemented through smart contracts is one of the most common scams on the blockchain platform. Although various learning-based Ponzi smart contract detection approaches have been proposed, they still suffer from several limitations, i.e., 1) extracting insufficient semantics and gathering Ponzi irrelevant components from the smart contract during feature engineering, and 2) underutilizing structured semantic features during model training. As the Ponzi scheme is an economic crime with the typical Rob-Peter-to-Pay-Paul transaction pattern, we propose a transaction semantic learning based approach to mitigate the above limitations. The fundamental idea of our approach is to represent the transaction-related semantics of a smart contract as a graph and utilize a graph convolutional network (GCN) to learn the potential Ponzi-like transaction pattern from it. We define a novel code representation named slice transaction property graph (sTPG) to represent the transaction-related semantics, which can encode multiple transaction-related semantics inside a smart contract function into a graph and eliminate other irrelevant fragments. Then, we propose a relation-sensitive GCN as the learning model to identify potential Ponzi-scheme-like transaction patterns from sTPG by considering both nodes and edges features in sTPG. We evaluate our approach on two datasets: 1) smart contracts collected from Forum and Public datasets, and 2) really deployed smart contracts on the Ethereum blockchain. The experiment results show that our approach outperforms the state-of-the-art learning-based approaches.
Background: This paper tackles the critical challenge of detecting fraudulent transactions within the Ethereum blockchain using machine learning techniques. With the burgeoning importance of blockchain, ensuring its security against fraudulent activities is crucial to prevent significant monetary losses. We utilized a public dataset comprising 9,841 Ethereum transactions, characterized by attributes such as gas price, transaction fee, and timestamp.Methods: Our approach is bifurcated into two core phases: data preprocessing and predictive modeling. In the data preprocessing phase, we meticulously process the dataset and extract pivotal features from transactions, setting the stage for efficient predictive modeling.Findings: For predictive modeling, we employed several machine learning algorithms to discern between fraudulent and legitimate transactions. Our evaluation encompassed algorithms like decision trees, logistic regression, gradient boosting, XGBoost, and an innovative hybrid model that melds random forests with deep neural networks (DNN).Novelty: Our findings underscore that the proposed model boasts a precision rate of 97.16%, marking a substantial leap in fraudulent transaction detection on the Ethereum blockchain in comparison to prevailing methodologies. This paper augments the current efforts aimed at bolstering the security of blockchain transactions using sophisticated analytical strategies..
This paper introduces an innovative approach to bolster financial fraud detection within the Bitcoin network using ensemble deep learning models. By synergistically merging ensemble techniques with state-of-the-art deep learning methodologies, this study creates a robust framework that enhances security and trust in financial systems. Through meticulous data preprocessing and feature engineering, the proposed ensemble model, comprising Multi-Layer Perceptron (MLP), Feedforward Neural Network (FNN), and Attention LSTM, undergoes comprehensive training and evaluation. Results underscore the ensemble's remarkable performance, surpassing individual models in accuracy, precision, and recall. Notably, the ensemble achieves an accuracy of 99.62%, along with exceptional precision and recall values exceeding 99%. These outcomes validate the ensemble's capacity to detect both fraudulent and legitimate transactions with unprecedented accuracy. By effectively combining advanced machine learning techniques with the intricacies of blockchain-based transactions, this research contributes to building a more secure and reliable financial ecosystem. The findings open avenues for future research, emphasizing the potential of ensemble deep learning models to fortify defenses against evolving financial fraud strategies, fostering trust and integrity in digital transactions.
Abstract With the rapid development of blockchain technology in the financial sector, the security of blockchain is being put to the test due to an increase in phishing fraud. Therefore, it is essential to study more effective measures and better solutions. Graph models have been proven to provide abundant information for downstream assignments. In this study, a graph‐based embedding classification method is proposed for phishing detection on Ethereum by modeling its transaction records using subgraphs. Initially, the transaction data of normal addresses and an equal number of confirmed phishing addresses are collected through web crawling. Multiple subgraphs using the collected transaction records are constructed, with each subgraph containing a target address and its nearby transaction network. To extract features of the addresses, a modified Graph2Vec model called imgraph2vec is designed, which considers block height, timestamp, and amount of transactions. Finally, the Extreme Gradient Boosting (XGBoost) algorithm is employed to detect phishing and normal addresses. The experimental results show that the proposed method achieves good performance in phishing detection, indicating the effectiveness of imgraph2vec in feature acquisition of transaction networks compared to existing models.
Zhutian Lin, Xi Xiao, Guangwu Hu, Bin Zhang · 6 authors
The exponential growth of Ethereum transactions has resulted in a significant increase in phishing scams, leading to substantial financial losses in recent years. Current machine/deep learning-based approaches for classification have been found to be inadequate for large-scale and label-imbalanced Ethereum scenarios. To address this issue, we propose Phish2vec, a novel network embedding approach that takes into account the transaction temporality and heterogeneity in detecting phishing scams on Ethereum. Our approach begins by producing a transaction sub-network through data collection and preprocessing, which includes a novel Statistics-Based Sampling (SBS) method to address label leakage. To generate sequences that contain more comprehensive information, we then utilize two different types of sequences generators: Temporal-based Sequences Generator (TSG) and Heterogeneous-based Sequences Generator (HSG). By concatenating the sequences generated by TSG and HSG together, and feeding them into Word2vec and Fully Connected neural network (FC), our approach can identify phishing accounts with an Fl-score as high as 82.05%, which significantly outperforms classic schemes such as DeepWalk (67.29%), Trans2vec (74.78%), and Node2vec (70.91%).
Cryptocurrencies are rapidly expanding and becoming vital in digital financial markets. However, the rise in cryptocurrency-related illicit activities has led to significant losses for users. To protect the security of these platforms, it is critical to identify illicit accounts effectively. Current detection methods mainly depend on feature engineering or are inadequate to leverage the complex information within cryptocurrency transaction networks, resulting in suboptimal performance. In this paper, we present DIAM, an effective method for detecting illicit accounts in cryptocurrency transaction networks modeled by directed multi-graphs with attributed edges. DIAM first features an Edge2Seq module that captures intrinsic transaction patterns from parallel edges by considering edge attributes and their directed sequences, to generate effective node representations. Then in DIAM, we design a multigraph Discrepancy (MGD) module with a tailored message passing mechanism to capture the discrepant features between normal and illicit nodes over the multigraph topology, assisted by an attention mechanism. DIAM integrates these techniques for end-to-end training to detect illicit accounts from legitimate ones. Extensive experiments, comparing against 15 existing solutions on 4 large cryptocurrency datasets of Bitcoin and Ethereum, demonstrate that DIAM consistently outperforms others in accurately identifying illicit accounts. For example, on a Bitcoin dataset with 20 million nodes and 203 million edges, DIAM attains an F1 score of 96.55%, markedly surpassing the runner-up's score of 83.92%. The code is available at https://github.com/TommyDzh/DIAM.
The Ponzi scheme, an old-fashioned fraud, is now popular on the Ethereum blockchain, causing considerable financial losses to many crypto investors. A few Ponzi detection methods have been proposed in the literature, most of which detect a Ponzi scheme based on its smart contract source code. This contract-code-based approach, while achieving very high accuracy, is not robust because a Ponzi developer can fool a detection model by obfuscating the opcode or inventing a new profit distribution logic that cannot be detected. On the contrary, a transaction-based approach could improve the robustness of detection because transactions, unlike smart contracts, are harder to be manipulated. However, the current transaction-based detection models achieve fairly low accuracy. In this paper, we aim to improve the accuracy of the transaction-based models by employing time-series features, which turn out to be crucial in capturing the life-time behaviour a Ponzi application but were completely overlooked in previous works. We propose a new set of 85 features (22 known account-based and 63 new time-series features), which allows off-the-shelf machine learning algorithms to achieve up to 30% higher F1-scores compared to existing works.
Tran Viet Khoa, Do Hai Son, Chi-Hieu Nguyen, Dinh Thai Hoang · 11 authors
With the escalating prevalence of malicious activities exploiting vulnerabilities in blockchain systems, there is an urgent requirement for robust attack detection mechanisms. To address this challenge, this paper presents a novel collaborative learning framework designed to detect attacks in blockchain transactions and smart contracts by analyzing transaction features. Our framework exhibits the capability to classify various types of blockchain attacks, including intricate attacks at the machine code level (e.g., injecting malicious codes to withdraw coins from users unlawfully), which typically necessitate significant time and security expertise to detect. To achieve that, the proposed framework incorporates a unique tool that transforms transaction features into visual representations, facilitating efficient analysis and classification of low-level machine codes. Furthermore, we propose an advanced collaborative learning model to enable real-time detection of diverse attack types at distributed mining nodes. Our model can efficiently detect attacks in smart contracts and transactions for blockchain systems without the need to gather all data from mining nodes into a centralized server. In order to evaluate the performance of our proposed framework, we deploy a pilot system based on a private Ethereum network and conduct multiple attack scenarios to generate a novel dataset. To the best of our knowledge, our dataset is the most comprehensive and diverse collection of transactions and smart contracts synthesized in a laboratory for cyberattack detection in blockchain systems. Our framework achieves a detection accuracy of approximately 94% through extensive simulations and 91% in real-time experiments with a throughput of over 2,150 transactions per second.
In recent years, blockchain technology has introduced decentralized finance (DeFi) as an alternative to traditional financial systems. DeFi aims to create a transparent and efficient financial ecosystem using smart contracts and emerging decentralized applications. However, the growing popularity of DeFi has made it a target for fraudulent activities, resulting in losses of billions of dollars due to various types of frauds. To address these issues, researchers have explored the potential of artificial intelligence (AI) approaches to detect such fraudulent activities. Yet, there is a lack of a systematic survey to organize and summarize those existing works and to identify the future research opportunities. In this survey, we provide a systematic taxonomy of various frauds in the DeFi ecosystem, categorized by the different stages of a DeFi project's life cycle: project development, introduction, growth, maturity, and decline. This taxonomy is based on our finding: many frauds have strong correlations in the stage of the DeFi project. According to the taxonomy, we review existing AI-powered detection methods, including statistical modeling, natural language processing and other machine learning techniques, etc. We find that fraud detection in different stages employs distinct types of methods and observe the commendable performance of tree-based and graph-related models in tackling fraud detection tasks. By analyzing the challenges and trends, we present the findings to provide proactive suggestion and guide future research in DeFi fraud detection. We believe that this survey is able to support researchers, practitioners, and regulators in establishing a secure and trustworthy DeFi ecosystem.
The advancement of technology has given a new dimension to various sectors and this paper particularly talks about banking sector. The purpose of writing this paper is to understand how the technology such Artificial intelligence (AI) and Blockchain works in the various elements of the financial sector to make it more effective with optimum utilization of resources, accuracy of predictions and decisions. This study also discusses about the application of blockchain technology in the banking as it ensures faster, secure and authentic data transactions along with customer services as a result of which it is found that the introduction of technology has gave a new life to Banking sector by simplifying the complex works, managing huge volume of financial data, taking appropriate decisions for investors and traders and also generate predictions according to which they can invest their money to get maximum out of it . The adoption of AI and blockchain is unprecedently increasing from time to time in the banking sector. However, the blockchain implementation in the banking sector also face many challenges. This research provides certain recommendations one of which is adopting the integrated AI - Blockchain model, which will be proved to be a boon for all the banks to store huge financial data and perform complex task as this model is much safer and effective in providing maximum security, privacy and accuracy and certain other suggestions.
The introduction of smart contracts has brought new opportunities to the development of blockchain. However, due to the potential security vulnerabilities in smart contracts, accurately identifying these vulnerabilities has become one of the key challenges. Existing detection methods mostly focus on open-source smart contracts and suffer from issues such as low data utilization, insufficient contract information extraction, and high false positive rates. Since the proportion of open-source contracts is extremely low, accurately extracting feature information from non-open-source contracts and identifying vulnerabilities has become an urgent problem to be solved. Therefore, we propose SCOBERT, a pre-training model for blockchain smart contracts. SCOBERT supports downstream tasks related to smart contracts, such as smart contract functionality identification and smart contract vulnerability detection. We develop SCOBERT using Transformer neural architecture and train it through pre-training tasks like MLM(Masked Language Model) and NSP(Next Sentence Prediction). This allows us to make full use of unlabeled smart contract data and capture the semantic information of smart contract opcode sequences effectively. We conduct experiments on three types of contract vulnerabilities: integer overflow, multiplication after division, and reentrancy, and validate them on the validation set. The experimental results demonstrate that the smart contract vulnerability detection method based on the SCOBERT pre-training model performs excellently in terms of accuracy, precision, recall, and F1 score.