Blockchain Papers

Jagendra Singh, Dinesh Prasad Sahu, Shreyans Murkute, U.S. Yadav · 6 authors

No abstract is available for this record.

Lee Song Haw Colin, P. Mohan, Jonathan Pan, Peter K. K. Loh

Smart contract vulnerabilities have led to substantial disruptions, ranging from the DAO attack to the recent Poolz Finance. While initially, the smart contract vulnerability definition lacked standardization, even with the advancements in Solidity, the potential for deploying malicious contracts to exploit legitimate ones persists. The Abstract syntax tree (AST), opcodes, and control flow graph (CFG) are the intermediate representations for Solidity contracts. In this paper, we propose an integrated and efficient smart contract vulnerability detection algorithm based on Multi-layer perceptron (MLP). We use feature vectors from the Opcodes and CFG for the machine learning (ML) model training. The existing ML-based approaches for analyzing the smart contract code are constrained by the vulnerability detection space, significantly varying Solidity versions, and no unified approach to verify against the ground truth. The primary contributions in this paper are (i) a standardized pre-processing method for smart contract training data, (ii) introducing bugs to create a balanced dataset of flawed files across Solidity versions using AST, and (iii) standardizing vulnerability identification using the Smart Contract Weakness Classification (SWC) registry. The ML models employed for benchmarking the proposed MLP, and a multi-input model combining MLP and Long short-term memory (LSTM) in our study are Random forest (RF), XGBoost (XGB), Support vector machine (SVM). The performance evaluation onreal-timesmart contracts deployed on the Ethereum Blockchain show an accuracy of up to 91% using MLP with the lowest average False Positive Rate (FPR) among all tools and models, measuring at 0.0125.

Jieli Liu, J. Chen, Jiajing Wu, Zhiying Wu · 6 authors

As one of the most typical cybercrime types, phishing scams have extended the devil’s hand to the emerging blockchain ecosystem in recent years. Especially, huge economic losses have been caused by phishing scams in Ethereum, the second-largest blockchain system. Existing approaches for Ethereum phishing detection, however, typically use machine learning or transaction graph embedding methods to identify phishers in isolation and do not effectively uncover the group of transaction accounts linked to scams (which we term a “gang”). Since accounts are pseudonymous in Ethereum, these undisclosed conspirator accounts have potential risks to the system. In this paper, we conduct the first study that characterizes and detects Ethereum phishing gangs. We first investigate the transaction behaviors in phishing gangs from the perspectives of individuals, pairs, and higher-order patterns. Our analysis reveals that although the Ethereum transaction graph is sparse with a highly skewed degree distribution, phishing accounts in the same gang have closer relationships and share specific transaction patterns. Based on our findings, we formalize the phishing gang detection problem and introduce a novel detection model named PGDetector. Given a risky phishing account as a seed, PGDetector can find out the potential risky accounts sharing close relationships within the seed’s community based on genetic algorithm optimization. Experimental results on large-scale Ethereum transaction data demonstrate the effectiveness of PGDetector.

Shaoyan CHEN, Fei Li

Abstract Blockchain smart contracts are codes that can execute and enforce rules for blockchain digital transactions. However, smart contracts may contain numerous subtle vulnerabilities, among which Ponzi vulnerabilities are notable. Existing Ponzi scheme contract detection approaches often rely on machine learning models trained on manually extracted features to achieve satisfactory classification results. Nonetheless, the code of a smart contract potentially harbours elusive semantics and characteristics, which compromises the precision and accuracy of vulnerability detection. Therefore, this paper proposes a method of converting operation codes into sequences to process data to avoid losing unnecessary important information, and uses a one‐dimensional convolutional neural network combined with formal verification. This method is named PZ‐C1DZ3(Ponzi‐Conv1D‐Z3) and is used for Ponzi scheme detection. Four types of machine learning models, namely Conv1D, Conv1D‐LSTM, Conv1D‐MLP, and Conv1D‐transformer, are employed for improvement and comparative validation experiments. Additionally, formal verification tool Z3 solver is utilized to conduct formal security verification on the final model, ensuring its safety. Experimental results demonstrate that the improved Conv1D model outperforms other existing models in terms of detection efficiency and accuracy while also meeting the requirements of formal security verification.

Ismail Alarab, Simant Prakoonwit

Abstract Money laundering has urged the need for machine learning algorithms for combating illicit services in the blockchain of cryptocurrencies due to its increasing complexity. Recent studies have revealed promising results using supervised learning methods in classifying illicit Bitcoin transactions of Elliptic data, one of the largest labelled data of Bitcoin transaction graphs. Nonetheless, all learning algorithms have failed to capture the dark market shutdown event that occurred in this data using its original features. This paper proposes a novel method named recurrent graph neural network model that extracts the temporal and graph topology of Bitcoin data to perform node classification as licit/illicit transactions. The proposed model performs sequential predictions that rely on recent labelled transactions designated by antecedent neighbouring features. Our main finding is that the proposed model against various models on Elliptic data has achieved state-of-the-art with accuracy and $$f_1$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mi>f</mml:mi> <mml:mn>1</mml:mn> </mml:msub> </mml:math> -score of 98.99% and 91.75%, respectively. Moreover, we visualise a snapshot of a Bitcoin transaction graph of Elliptic data to perform a case study using a backward reasoning process. The latter highlights the effectiveness of the proposed model from the explainability perspective. Sequential prediction leverages the dynamicity of the graph network in Elliptic data.

Yang Xikang, Biyu Zhou, Xuehai Tang, Zhang Xiao-dan · 6 authors

In recent years, the cryptocurrency platform becomes a prime target of various cybercrimes. Criminals use phishing fraud to commit massive scams on Ethereum (one of the most widely used cryptocurrency platforms), which poses a significant threat to the security of the cryptocurrency ecosystem. In this context, the use of Ethereum transaction information to detect and identify phishing fraud accounts is essential to ensure a secure and regulated trading platform. However, the previous proposals do not explore the behavior patterns of phishing accounts in depth, and also lack interpretability. To address this problem, we propose a novel and interpretable Ethereum phishing fraud detection method by extracting more fine-grained and interpretable account transaction features. The key idea is to extract both the spatial structure and temporal behavior patterns of the Ethereum transaction network as the “Translets” features via the highly interpretable attribute sub graphs and subsequences. Based on these features, a classifier with good interpretability is adopted, and the proposed interpreter is combined to interpret the detection outputs. The experimental results on real-world Ethereum phishing fraud account datasets demonstrate that our method not only has advantages in precision, recall, and F1 score but also provides interpretability in recognizing Ethereum phishing accounts.

Vishnu Kumar, Pisipati Pranav, M. Srinivas

The use of Smart Contracts and Blockchains has experienced a significant rise, leading to the automation of various financial and corporate operations. However, the occurrence of flaws and vulnerabilities in smart contracts has resulted in significant financial losses, raising concerns about their security. It is crucial to enhance the maintenance and reliability of smart contract codes. To detect the clones and bugs in a smart contract, in this paper, we propose a deep learning based model that learns the embedding as a continuous numeric-valued vector for each smart contract. Our approach involves five steps. First, we divide the smart contract Solidity program into streams along with their corresponding structural information. Second, we tokenize the textual data of the smart contract and create a corpus. Third, we employ the BERT word embedding model on the smart contract’s tokens corpus to learn feature representation for each token, generating a fixed-length vector of size 768. Fourth, we compute the embedding of each smart contract by considering the weighted sum of tokens within the contract. Finally, to measure clone similarity, we use hierarchical clustering on the feature vectors of smart contracts. The experimental results obtained using our approach on 22,000 Ethereum blockchain Solidity contracts show a clone ratio of 92.14%, and a precision of 93% in detecting clone-related bugs, representing significantly higher accuracy compared to conventional algorithms.

Mafas Raheem, Nirase Fathima Abubacker

Blockchain technologies for cryptocurrency applications have gotten a lot of attention and popularity among researchers and public consumers in recent years. The advent of cryptocurrency technology has defined the feature of trading currencies without a central authority. The anonymity nature of blockchain cryptocurrencies has caused a rise in illegal activities such as money laundering, ransomware attack payments, dark web payment transactions and cryptocurrencies could be one of the largest unregulated financial markets. This research focuses mainly on the second-largest cryptocurrency by market capitalization known as Ethereum to develop a prevention fraud detection model to detect any forms of illegal or fraudulent transactions in the markets. The experimented predictive models are Random Forest, Support Vector Machines, and K Nearest Neighbour. From the experiments, Random Forest achieved the highest f1 score of 0.98 amongst the three predictive models.

Fatih Rabia, Sara Arezki, Taoufiq Gadi

The emergence of blockchain has ushered in a significant transformation in information systems research. Blockchain’s key pillars such as decentralization, immutability, and transparency have paved the path for extensive exploration in various research domains. This particular study is focused on electronic voting, aiming to improve voting procedures by making better use of the benefits offered by blockchain technology. Through a comprehensive review of existing literature, we highlight the potential benefits of blockchain-based electronic voting systems such as transparency, security, and efficiency. However, several challenges, such as scalability, personal data confidentiality, and ensuring robust identity verification, persist. Addressing these issues is necessary to unlock the full potential of blockchain-based electronic voting systems, thereby fostering the development of trustworthy election systems in the future.

Hanyang Guo, Y. Chen, Xiangping Chen, Yuan Huang · 5 authors

A smart contract is a kind of code deployed on the blockchain that executes automatically once an event triggers a clause in the contract. Since smart contracts involve businesses such as asset transfer, they are more vulnerable to attacks, so it is crucial to ensure the security of smart contracts. Because a smart contract cannot be tampered with once deployed on the blockchain, for smart contract developers, it is necessary to fix vulnerabilities before deployment. Compared with many vulnerability detection tools for smart contracts, the amount of automatic fix approaches for smart contracts is relatively limited. These approaches mainly use defined pattern-based methods or heuristic search algorithms for vulnerability repairs. In this article, we propose RLRep , a reinforcement learning-based approach to provide smart contract repair recommendations for smart contract developers automatically. This approach adopts an agent to provide repair action suggestions based on the vulnerable smart contract without any supervision, which can solve the problem of missing labeled data in machine learning-based repair methods. We evaluate our approach on a dataset containing 853 smart contract programs (programming language: Solidity) with different kinds of vulnerabilities. We split them into training and test sets. The result shows that our approach can provide 54.97% correct repair recommendations for smart contracts.

C. Madana Kumar Reddy, Rakesh Chandrashekar, K Nattar Kannan, H Pal Thethi · 6 authors

Software Defined Network (SDN) has permitted revolutionary networking solutions by the separation of manage and statistics planes and the centralization of network administration. Nevertheless, SDN networks without robust get right of access to manage may be prone to protection breaches and unapproved gain admission to, consequently giving significant hazards. Rapid and accurate anomaly detection and access control are important in cloud-aspect collaborative networks, given to the fact permitted devices have the opportunity to turn malevolent. We suggest the exploitation of a modern cloud-primarily based collaboration network architecture that makes use of SDN and neural networks to solve these challenging circumstances. Attribute-Based Access management (ABAC) and smart contracts give accurate community device access management in our machine. In addition, we present a totally new approach for identifying anomalies in Cloud-Edge Collaborative (KPI) data with the assistance of the employment of an effective aggregate of GRU-GAN. This hybrid technique finds prevalent devices, enabling preemptive discount of dangers. This response moreover employs blockchain era to beautify protection. The decentralised and tamper-evident structure of blockchain promotes obtain right of entry to manage and ensures the integrity of community transactions. Experimental effects argue that our method discovers irregularities greater across datasets. Network integrity is secured by the implementation of popularity-based get right of access to rules, which minimise malicious tool assaults. This full strategy blends SDN, neural networks, and blockchain generation to defend cloud-location collaboration networks against unapproved get right of access to and criminal hobby. This specialised technique secures network assets and creates the basis for current day-day community infrastructures to be lasting and truthful.

Udit Agarwal, Vinay Rishiwal, Sudeep Tanwar, Mano Yadav

Abstract In the past few years, cryptocurrency has gained widespread acceptance because of its decentralized nature, quick and secure transactions, and potential for investment and speculation. But the increased popularity has also led to increased cryptocurrency fraud, including scams, phishing attacks, Ponzi schemes, and other criminal activities. Although there is little documentation of cryptocurrency fraud, an in‐depth study is essential to recognize various scams in different cryptocurrencies. To fill this gap, a study investigated cryptocurrency‐related fraud in various cryptocurrencies and provided a taxonomy of crypto‐forensics and forensic blockchain. In addition, we have introduced an architecture that integrates artificial intelligence (AI) and blockchain technologies to investigate and protect against instances of cryptocurrency fraud. The suggested design's effectiveness was evaluated using several machine learning (ML) classification algorithms. The conclusion of the evaluation confirmed that the random forest (RF) classifier performed the best, delivering the highest level of accuracy, that is, 97.5%. Once the ML classifiers detect cryptocurrency fraud, the information is securely stored in the InterPlanetary File System (IPFS); the document's hash is also stored in the blockchain using smart contracts. Law enforcement can leverage blockchain technology to secure access to fraudulent cryptographic transactions. The proposed architecture was tested for bandwidth utilization. Despite the potential benefits of blockchain and crypto‐forensics, several issues and challenges remain, including privacy concerns, standardization, and difficulty identifying fraud between crypto‐currencies. Finally, the paper discusses various problems and challenges in blockchain and crypto forensics to investigate cryptocurrency fraud.

Charles Rawlins, S. Jagannathan

Decision-making and consensus in traditional blockchain protocols is formulated as a repeated Bernoulli trial that solves a computationally-intense lottery puzzle, called Proof-of-Work (PoW) in Bitcoin. This approach has shown robustness through practice, but does not scale with increasing network size and generation of new transactions. Resource constrained Internet of Things (IoT) networks are incompatible with full computation of schemes like Bitcoin's PoW. Our effort proposes a first step towards an alternative consensus using machine learning-based decision-making with prediction of fraud transactions to alleviate need for intense computation. To improve base approval probabilities for fraud detection in an ideal security setting, Vector GAN (VecGAN) is proposed to augment blockchain data in classifier training, which combines error-driven learning with Bayesian estimation to alleviate calculations. This two-step approach with augmentation and classification on new transactions is proposed as a novel approach to blockchain decision-making. Experimental prediction accuracy using VecGAN improved up to 3% on simplistic classifiers compared to other state-of-the-art augmentation techniques. Resource consumption in a realistic blockchain setting was reduced while improving block throughput by 50% compared to PoW. Future work will explore Sybil-spam defensive measures for realistic protocol implementation with this approach.

M. Mazhar Rathore, Sushil S. Chaurasia, Dhirendra Shukla, Prashant Anand

Due to the rise in the use of crypto-currencies, such as Bitcoin and Ethereum, the fraud activities in the financial sector are increasing at the same pace. It becomes very challenging to detect frauds in crypto-currencies, because of it's distributed and anonymized nature and not having central control. In this paper, we exploited the decision-tree based machine learning model using a boosting approach, particularly XGBoost, to identify the fraudulent addresses in the Ethereum crypto-currency. To select a best decision tree and learning approach on our fraud dataset, initially, we chose four highly performed decision tree learning approaches including CART, random forest, LGBM, XGBoost, and applied a cross validation mechanism to select the top one based on accuracy. Among CART, random forest, gradient boosting tree, we selected the XGBoost model as the final model and tuned it for the best hyper parameters. Finally, we built the model on 80% of the training data, which has produced accuracy of more than 96% on test data. Further, the model is highly efficient to work in a real environment, as proved by running extensive experiments.

Xiaojin Wang, Yanna Zhang, Fangfang Chen

In the current task of text classification for smart contracts, the role of labels in the final classification performance is relatively small, and label information has not been better utilized. In order to make effective use of label information, this paper proposes a smart contract classification method based on label embedding and collaborative attention mechanism. This method introduces a collaborative attention mechanism to generate semantic representations of smart contracts related to labels and smart contract semantic vectors. This approach enables the classification model to focus on the relevant parts of both, thereby effectively improving the accuracy of classification.

Shuxiao Song, Xiao Yu, Yuexuan Ma, Jiale Li · 5 authors

No abstract is available for this record.

Shuai Liu, Bo Cui, Wenhan Hou

No abstract is available for this record.

Xueyan Tang, Yuying Du, Alan Lai, Ze Zhang · 5 authors

This paper aims to explore the application of deep learning in smart contract vulnerabilities detection. Smart contracts are an essential part of blockchain technology and are crucial for developing decentralized applications. However, smart contract vulnerabilities can cause financial losses and system crashes. Static analysis tools are frequently used to detect vulnerabilities in smart contracts, but they often result in false positives and false negatives because of their high reliance on predefined rules and lack of semantic analysis capabilities. Furthermore, these predefined rules quickly become obsolete and fail to adapt or generalize to new data. In contrast, deep learning methods do not require predefined detection rules and can learn the features of vulnerabilities during the training process. In this paper, we introduce a solution called Lightning Cat which is based on deep learning techniques. We train three deep learning models for detecting vulnerabilities in smart contract: Optimized-CodeBERT, Optimized-LSTM, and Optimized-CNN. Experimental results show that, in the Lightning Cat we propose, Optimized-CodeBERT model surpasses other methods, achieving an f1-score of 93.53%. To precisely extract vulnerability features, we acquire segments of vulnerable code functions to retain critical vulnerability features. Using the CodeBERT pre-training model for data preprocessing, we could capture the syntax and semantics of the code more accurately. To demonstrate the feasibility of our proposed solution, we evaluate its performance using the SolidiFI-benchmark dataset, which consists of 9369 vulnerable contracts injected with vulnerabilities from seven different types.

Zhaowei Liu, Yixian Wang, Shenqiang Wang, Xiangfu Zhao · 6 authors

No abstract is available for this record.

Anusha Ramesh, Meera Eeswaran, Faros Faizdnor Roslan, Dependent Variable

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.

Aastha Suri, Muskan Rathore, Deepika Kumar, Aakansha Aakansha · 5 authors

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.

Anshika Sharma, Himanshi Babbar

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.

Leonid Garin, V. B. Gisin

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.