As the largest blockchain platform supporting smart contracts,millions of smart contracts have been deployed on Ethereum.Since the deployed smart contracts cannot be modified even if the contracts contain bugs,it is critical for developers to eliminate bugs prior to the deployment.Many smart contract analysis tools have been proposed.These tools either use bytecode-based symbolic execution to detect bugs,or convert the source code to an intermediate representation and then detect bugs.The tools based on symbolic execution usually cannot cover many types of bugs in source code.Converting the source code to an intermediate representation negatively impacts the detection speed.Moreover,these tools are bug detectors,which cannot automatically fix bugs based on analysis results.To address these limitations,we propose an approach named SolidityCheck,which employs regular expressions,program instrumentation and statement replacement in source code to quickly detect bugs and fix certain types of bugs.We conduct extensive experiments to evaluate SolidityCheck.The experimental results show that,compared with existing approaches,SolidityCheck demonstrates excellent performances on multiple indicators.
With the development of blockchain technologies, many Ponzi schemes disguise themselves under the veil of smart contracts. The Ponzi scheme contracts cause serious financial losses, which has a bad effect on the blockchain. Existing Ponzi scheme contract detection studies have mainly focused on extracting hand-crafted features and training a machine learning classifier to detect Ponzi scheme contracts. However, the hand-crafted features cannot capture the structural and semantic feature of the source code. Therefore, in this study, we propose a Ponzi scheme contract detection method called MTCformer (Multi-channel Text Convolutional Neural Networks and Transofrmer). In order to reserve the structural information of the source code, the MTCformer first converts the Abstract Syntax Tree (AST) of the smart contract code to the specially formatted code token sequence via the Structure-Based Traversal (SBT) method. Then, the MTCformer uses multi-channel TextCNN (Text Convolutional Neural Networks) to learn local structural and semantic features from the code token sequence. Next, the MTCformer employs the Transformer to capture the long-range dependencies of code tokens. Finally, a fully connected neural network with a cost-sensitive loss function in the MTCformer is used for classification. The experimental results show that the MTCformer is superior to the state-of-the-art methods and its variants in Ponzi scheme contract detection.
Júlia Almeida Valadares, Vinícius Cunha Oliveira, José Eduardo de Azevedo Sousa, Heder S. Bernardino · 7 authors
Ethereum é uma das maiores plataformas de cripto ativos atualmente, e vem se tornando um ambiente de negócios digitais entre usuários. O Ethereum foi concebido para permitir transações descentralizadas entre usuários anônimos. Contudo, o desenvolvimento de métodos para identificar perfis de comportamentos de usuários, mantendo suas identidades anônimas, têm o potencial para alavancar negócios nessa plataforma. Nesse trabalho, investigamos o uso de aprendizado de máquina para classificar um perfil de usuário como profissional ou comum a partir de atributos de suas transações. Essa classificação é desafiadora devido à pequena fração de usuários publicamente rotulados no Ethereum e ainda a fração consideravelmente menor de usuários profissionais. Para conduzir essa investigação, treinamos modelos considerando conjuntos cuidadosamente balanceados de transações com usuários rotulados. Nossos resultados mostram modelos de alto desempenho para a classificação de perfis, alcançando desempenho superior a 90% para acurácia, precisão, revocação e demais medidas relacionadas. Adicionalmente, identificamos as características mais relevantes em transações para essa classificação.
Chargeback fraud is a fast-growing threat to e-commerce, bringing huge losses to online sellers, but there is still a lack of effective technical counter measures. To combat chargeback fraud, this paper proposes a consortium blockchain based chargeback fraud data sharing mechanism — CFLedger, which includes multi-source reporting, anti-tamper accounting, and post-supervision. This paper also analyzes the efficiency, effectiveness, and practicality of CFLedger, proving that it is an effective and feasible mechanism to prevent chargeback fraud.
Smart contract security is one of core security issues in the application of blockchain. In recent years, attacks on smart contracts occur frequently, there are a lot of researches concerning on smart contract security issues. However, almost all solutions proposed in these researches are low precision and high False Negative Rate(FNR). In this paper, we propose a defect detection method for checking security of Solidity smart contract based on knowledge graph. Therefore, we first construct knowledge graph of smart contracts by fully integrating syntax and semantic information of Solidity source code; then, we define defect patterns by analyzing defect characteristics; furthermore, we define inference rules for defects based on knowledge graph and defect patterns; finally, we detect defects by SPARQL query. We also implement a tool named SolDetector and perform experiment on three different datasets, which shows that SolDetector is effective and efficient.
In recent years, phishing scams have become the crime type with the largest money involved on Ethereum, the second-largest blockchain platform. Meanwhile, graph neural network (GNN) has shown promising performance in various node classification tasks. However, for Ethereum transaction data, which could be naturally abstracted to a real-world complex graph, the scarcity of labels and the huge volume of transaction data make it difficult to take advantage of GNN methods. Here in this paper, to address the two challenges, we propose a Self-supervised Incremental deep Graph learning model (SIEGE), for the phishing scam detection problem on Ethereum. In our model, two pretext tasks designed from spatial and temporal perspectives help us effectively learn useful node embedding from the huge amount of unlabelled transaction data. And the incremental paradigm allows us to efficiently handle large-scale transaction data and help the model maintain good performance when the data distribution is drastically changing. We collect transaction records about half a year from Ethereum and our extensive experiments show that our model consistently outperforms strong baselines in both transductive and inductive settings.
With the development of blockchain technologies, the number of smart contracts deployed on blockchain platforms is growing exponentially, which makes it difficult for users to find desired services by manual screening. The automatic classification of smart contracts can provide blockchain users with keyword-based contract searching and helps to manage smart contracts effectively. Current research on smart contract classification focuses on Natural Language Processing (NLP) solutions which are based on contract source code. However, more than 94% of smart contracts are not open-source, so the application scenarios of NLP methods are very limited. Meanwhile, NLP models are vulnerable to adversarial attacks. This paper proposes a classification model based on features from contract bytecode instead of source code to solve these problems. We also use feature selection and ensemble learning to optimize the model. Our experimental studies on over 11K real-world Ethereum smart contracts show that our model can classify smart contracts without source code and has better performance than baseline models. Our model also has good resistance to adversarial attacks compared with NLP-based models. In addition, our analysis reveals that account features used in many smart contract classification models have little effect on classification and can be excluded.
Rohan Kumar C L, Ali M. Zain, Ali M. Zain, A V Prajwal · 5 authors
Fraudulent transactions have a huge impact on the economy and trust of a blockchain network. Consensus algorithms like proof of work or proof of stake can verify the validity of the transaction but not the nature of the users involved in the transactions or those who verify the transactions. This makes a blockchain network still vulnerable to fraudulent activities. One of the ways to eliminate fraud is by using machine learning techniques. Machine learning can be of supervised or unsupervised nature. In this paper, we use various supervised machine learning techniques to check for fraudulent and legitimate transactions. We also provide an extensive comparative study of various supervised machine learning techniques like decision trees, Naive Bayes, logistic regression, multilayer perceptron, and so on for the above task.
Abstract Ethereum attracts extensive attention due to its distinctive function of smart contract and decentralized applications (Dapps). Since the number of contracts on blockchain has increased vigorously, various security vulnerabilities come up. Researchers rely on static symbolic analysis method at first, and it seems to perform well in the accuracy of vulnerability detection. However, this method requires manual analysis in advance and it needs to traverse all the possible execution paths to find out the vulnerable ones. The deeper the path goes, the more time it costs to detect the contracts. This paper proposes an approach to detect smart contracts vulnerability on blockchain by using machine learning(ML) methods. This approach aims to build a general benchmark for new vulnerability detection in order to reduce the demand of expert manpower. Moreover, the high-speed-performance ML algorithm makes quick detection comes true. As long as we adjust the threshold of the model, it can work as a fast prefilter for the traditional symbolic analysis tools in further improvement of accuracy.
Since its inception, Bitcoin has been subject to numerous thefts due to its enormous economic value. Hackers steal Bitcoin wallet keys to transfer Bitcoin from compromised users, causing huge economic losses to victims. To address the security threat of Bitcoin theft, supervised learning methods were used in this study to detect and provide warnings about Bitcoin theft events. To overcome the shortcomings of the existing work, more comprehensive features of Bitcoin transaction data were extracted, the unbalanced dataset was equalized, and five supervised methods—the k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), adaptive boosting (AdaBoost), and multi-layer perceptron (MLP) techniques—as well as three unsupervised methods—the local outlier factor (LOF), one-class support vector machine (OCSVM), and Mahalanobis distance-based approach (MDB)—were used for detection. The best performer among these algorithms was the RF algorithm, which achieved recall, precision, and F1 values of 95.9%. The experimental results showed that the designed features are more effective than the currently used ones. The results of the supervised methods were significantly better than those of the unsupervised methods, and the results of the supervised methods could be further improved after equalizing the training set.
Catarina Oliveira, João Torres, Maria Inês Silva, David Aparício · 6 authors
Money laundering is a global phenomenon with wide-reaching social and economic consequences. Cryptocurrencies are particularly susceptible due to the lack of control by authorities and their anonymity. Thus, it is important to develop new techniques to detect and prevent illicit cryptocurrency transactions. In our work, we propose new features based on the structure of the graph and past labels to boost the performance of machine learning methods to detect money laundering. Our method, GuiltyWalker, performs random walks on the bitcoin transaction graph and computes features based on the distance to illicit transactions. We combine these new features with features proposed by Weber et al. and observe an improvement of about 5pp regarding illicit classification. Namely, we observe that our proposed features are particularly helpful during a black market shutdown, where the algorithm by Weber et al. was low performing.
The paper-based certification is prone to manipulation and vulnerable to fraud. Instances of fraudulent degrees, manipulation of academic records, or compromised academic programs adversely impact and damage an academic institution's credibility. It also affects the Indian universities’ mission and prospects of the students graduating from such a university. What makes reputational risk a unique risk is that it may arise both from the university or institution's failure or the action outside the university. It is, therefore, essential to take an enterprise risk management approach to mitigate reputational risk. Robust credential verification and validation protocols are the most important protections against fake certifications. The legacy certificate verification solutions are highly centralized, i.e., utterly dependent on the issuing authority for certificates. Despite the University Grants Commission (UGC) taking strict measures against individuals, Indian universities, colleges, and associations, we do come across several acts of torts. Some of the technology-savvy institutions have moved to digital certificates and digital signatures. However, this has an inherent weakness, i.e., they still need to rely on a trusted third party. Blockchain technology has three foundational components, data structures based on cryptography that make it secure and tamperproof, consensus protocols that allow it to function truthfully and without any central authority or a third party smart contracts, which provide efficiency and business value transactions. These key features of blockchain, if implemented appropriately, effectively has the potential to mitigate the inherent reputational risk arising from fraudulent academic certificate matters. Niti Ayog is currently developing a blockchain-based proof of concepts to solve traditional educational qualifications related to identity misrepresentation and document forgery. The immutability attribute of the blockchain ensures that tampering and manipulation of the record are not attainable. This paper focuses on the reputational risk Indian universities and institution may face when its certifications are not easily verifiable. Therefore, it becomes easy targets for bad actors to exploit vulnerabilities by issuing counterfeit certificates. Secondary published data, including various scholarly journals, reports, industry publications, and website sources, are utilized to develop this case study. The paper also explores how blockchain technology with specific reference to the proof of concept SuperCert proposed by Niti Ayog for Indian academic institutions may provide effective preventive control to overcome such reputational risk using the ABCD analysis framework as a research case study.
With the popularity of blockchain technology, the financial security issues of blockchain transaction networks have become increasingly serious. Phishing scam detection methods will protect possible victims and build a healthier blockchain ecosystem. Usually, the existing works define phishing scam detection as a node classification task by learning the potential features of users through graph embedding methods such as random walk or graph neural network (GNN). However, these detection methods are suffered from high complexity due to the large scale of the blockchain transaction network, ignoring temporal information of the transaction. Addressing this problem, we defined the transaction pattern graphs for users and transformed the phishing scam detection into a graph classification task. To extract richer information from the input graph, we proposed a multi-channel graph classification model (MCGC) with multiple feature extraction channels for GNN. The transaction pattern graphs and MCGC are more able to detect potential phishing scammers by extracting the transaction pattern features of the target users. Extensive experiments on seven benchmark and Ethereum datasets demonstrate that the proposed MCGC can not only achieve state-of-the-art performance in the graph classification task but also achieve effective phishing scam detection based on the target users' transaction pattern graphs.
For long, different e-voting systems have been provided with the goal of increasing security and minimizing cost. Blockchain is a major breakthrough in the technological industry that provide immense secured platform. With the launch of Ethereum, a decentralized platform which runs decentralized applications (DApps) on it, a secured voting system now seems possible. Many organizations have now shifted their focus on voting through blockchain platforms. There’s a very high chance that a normal voting method won’t lead to a clear majority. There can be many ways to deal with this issue which includes another voting process to take place which can be quite expensive in terms of time and resources. In our paper, we introduce the vote-trading concept where the votes can be redistributed to other candidates in case if there is no clear majority and also this ‘ majority’ factor can be set by the organization according to their requirement. We discuss the design for the blockchain based preferential e-voting system using the Solidity programming language where instead of one vote per candidate, we provide the concept of giving preference to the candidates.
Elizaveta Zinovyeva, Raphael Constantin Georg Reule, Wolfgang Karl Härdle
Smart Contracts are commonly considered to be an important component or even a key to many business solutions in an immense variety of sectors and promises to securely increase their individual efficiency in an ever more digitized environment. Introduced in the early 1990's, the technology has gained a lot of attention with its application to blockchain technology to an extent, that can be considered a veritable hype. Reflecting the growing institutional interest, this intertwined exploratory study between statistics, information technology, and law contrasts these idealistic stories with the data reality and provides a mandatory step of understanding the matter, before any further relevant applications are discussed as being "factually" able to replace traditional constructions. Besides fundamental flaws and application difficulties of currently employed Smart Contracts, the technological drive and enthusiasm backing it may however serve as a jump-off board for future developments thrusting well in the presently unshakeable traditional structures.
The emergence of smart contracts has increased the attention of industry and academia to blockchain technology, which is tamper-proofing, decentralized, autonomous, and enables decentralized applications to operate in untrustworthy environments. However, these features of this technology are also easily exploited by unscrupulous individuals, a typical example of which is the Ponzi scheme in Ethereum. The negative effect of unscrupulous individuals writing Ponzi scheme-type smart contracts in Ethereum and then using these contracts to scam large amounts of money has been significant. To solve this problem, we propose a detection model for detecting Ponzi schemes in smart contracts using bytecode. In this model, our innovation is shown in two aspects: We first propose to use two bytes as one characteristic, which can quickly transform the bytecode into a high-dimensional matrix, and this matrix contains all the implied characteristics in the bytecode. Then, We innovatively transformed the Ponzi schemes detection into an anomaly detection problem. Finally, an anomaly detection algorithm is used to identify Ponzi schemes in smart contracts. Experimental results show that the proposed detection model can greatly improve the accuracy of the detection of the Ponzi scheme contracts. Moreover, the F1-score of this model can reach 0.88, which is far better than those of other traditional detection models.
Shanqing Yu, Jie Jin, Yunyi Xie, Jie Shen · 5 authors
With the rapid growth of blockchain, an increasing number of users have been attracted and many implementations have been refreshed in different fields. Especially in the cryptocurrency investment field, blockchain technology has shown vigorous vitality. However, along with the rise of online business, numerous fraudulent activities, e.g., money laundering, bribery, phishing, and others, emerge as the main threat to trading security. Due to the openness of Ethereum, researchers can easily access Ethereum transaction records and smart contracts, which brings unprecedented opportunities for Ethereum scams detection and analysis. This paper mainly focuses on the Ponzi scheme, a typical fraud, which has caused large property damage to the users in Ethereum. By verifying Ponzi contracts to maintain Ethereum's sustainable development, we model Ponzi scheme identification and detection as a node classification task. In this paper, we first collect target contracts' transactions to establish transaction networks and propose a detecting model based on graph convolutional network (GCN) to precisely distinguishPonzi contracts. Experiments on different real-world Ethereum datasets demonstrate that our proposed model has promising results compared with general machine learning methods to detect Ponzi schemes.
A rede Bitcoin é um sucesso por permitir a transferência de criptomoeda com um baixo custo, de forma rápida, sem limites geográficos e sem a intervenção de um banco intermediador. Está sendo apontada como uma possível solução para mais de um bilhão de pessoas que não tem acesso ao sistema financeiro por causa dos altos custos. Por outro lado, a rede Biticoin é pseudo-anônima e tem sido usada para uma enorme variedade de atividades financeiras dúbias e ilegais. Este artigo investiga as atividades de lavagem de dinheiro na rede Bitcoin através de diversos mecanismos que procuram melhorar o desempenho de classificadores na análise de um conjunto de dados desbalanceado devido a uma classe minoritária com muito poucas amostras. A análise considera o conjunto de dados Elliptic com mais de 200 mil transações de Bitcoin, sendo o maior conjunto rotulado de dados publicamente disponível que existe hoje de todas as criptomoedas. Os experimentos realizados mostram a eficácia de cada estratégia na melhora da classificação das atividades de lavagem de dinheiro tais como: i) o percentual de repartição do conjunto de dados em treino e teste; ii) heurísticas de sobre-amostragem; ii) diferentes algoritmos de aprendizado de máquina; iv) algoritmo de reforço de aprendizado adaptativo e v) descoberta automática de características. Os resultados mostram um bom desempenho do algoritmo de sobre-amostragem AdaSyn e que o maior ganho em desempenho foi com o classificador floresta aleatória.
The use of containers in cloud computing has been steadily increasing. With the emergence of Kubernetes, the management of applications inside containers (or pods) is simplified. Kubernetes allows automated actions like self-healing, scaling, rolling back, and updates for the application management. At the same time, security threats have also evolved with attacks on pods to perform malicious actions. Out of several recent malware types, cryptomining has emerged as one of the most serious threats with its hijacking of server resources for cryptocurrency mining. During application deployment and execution in the pod, a cryptomining process, started by a hidden malware executable can be run in the background, and a method to detect malicious cryptomining software running inside Kubernetes pods is needed. One feasible strategy is to use machine learning (ML) to identify and classify pods based on whether or not they contain a running process of cryptomining. In addition to such detection, the system administrator will need an explanation as to the reason(s) of the ML's classification outcome. The explanation will justify and support disruptive administrative decisions such as pod removal or its restart with a new image. In this article, we describe the design and implementation of an ML-based detection system of anomalous pods in a Kubernetes cluster by monitoring Linux-kernel system calls (syscalls). Several types of cryptominers images are used as containers within an anomalous pod, and several ML models are built to detect such pods in the presence of numerous healthy cloud workloads. Explainability is provided using SHAP, LIME, and a novel auto-encoding-based scheme for LSTM models. Seven evaluation metrics are used to compare and contrast the explainable models of the proposed ML cryptomining detection engine.
With the advance of Bitcoin technology, money laundering has been incentivised as a den of Bitcoin blockchain, in which the user's identity is hidden behind a pseudonym known as address. Although this trait permits concealing in the plain sight, the public ledger of Bitcoin blockchain provides more power for investigators and allows collective intelligence for anti-money laundering and forensic analysis. This fascinating paradox arises in the strength of Bitcoin technology. Machine learning techniques have attained promising results in forensic analysis, in order to spot suspicious behaviour in Bitcoin blockchain. This paper presents a comparative analysis of the performance of classical supervised learning methods using a recently published data set derived from Bitcoin blockchain, to predict licit and illicit transactions in the network. Besides, an ensemble learning method is utilised using a combination of the given supervised learning models, which outperforms the given classical methods. This experiment is performed using a newly published data set derived from Bitcoin blockchain. Our main contribution points out that using ensemble learning approach outperforms the performance of the classical learning models used in the original paper, using Elliptic data set, a time series of Bitcoin transaction graph with node transactions and directed payments flow edges. Using the same data set, we show that we are able to predict licit/illicit transactions with an accuracy of 98.13% and F1 score equals to 83.36% using the proposed method. We discuss the variety of supervised learning methods, and their capabilities of assisting forensic analysis, and propose future work directions.
Joana Lorenz, Maria Inês Silva, David Aparício, João Tiago Ascensão · 5 authors
Every year, criminals launder billions of dollars acquired from serious felonies (e.g., terrorism, drug smuggling, or human trafficking), harming countless people and economies. Cryptocurrencies, in particular, have developed as a haven for money laundering activity. Machine Learning can be used to detect these illicit patterns. However, labels are so scarce that traditional supervised algorithms are inapplicable. Here, we address money laundering detection assuming minimal access to labels. First, we show that existing state-of-the-art solutions using unsupervised anomaly detection methods are inadequate to detect the illicit patterns in a real Bitcoin transaction dataset. Then, we show that our proposed active learning solution is capable of matching the performance of a fully supervised baseline by using just 5% of the labels. This solution mimics a typical real-life situation in which a limited number of labels can be acquired through manual annotation by experts.
Francesco Zola, Jan L. Bruse, Xabier Etxeberria Barrio, Mikel Galar · 5 authors
In Bitcoin entity classification, results are strongly conditioned by the ground-truth dataset, especially when applying supervised machine learning approaches. However, these ground-truth datasets are frequently affected by significant class imbalance as generally they contain much more information regarding legal services (Exchange, Gambling), than regarding services that may be related to illicit activities (Mixer, Service). Class imbalance increases the complexity of applying machine learning techniques and reduces the quality of classification results, especially for underrepresented, but critical classes. In this paper, we propose to address this problem by using Generative Adversarial Networks (GANs) for Bitcoin data augmentation as GANs recently have shown promising results in the domain of image classification. However, there is no "one-fits-all" GAN solution that works for every scenario. In fact, setting GAN training parameters is non-trivial and heavily affects the quality of the generated synthetic data. We therefore evaluate how GAN parameters such as the optimization function, the size of the dataset and the chosen batch size affect GAN implementation for one underrepresented entity class (Mining Pool) and demonstrate how a "good" GAN configuration can be obtained that achieves high similarity between synthetically generated and real Bitcoin address data. To the best of our knowledge, this is the first study presenting GANs as a valid tool for generating synthetic address data for data augmentation in Bitcoin entity classification.
Shakkeera L, Hem Pransanth K C, Sabareesh, Sumaiya Begum · 5 authors
In today’s era, the cloud database security is one of the main concerns for any of the real time data accessing web/mobile applications. The cloud database protection involves accessibility and vulnerability of data, data protection, storage space, integrity and confidentiality on sensitive data. Building an electronic voting system that tries to completely fulfill the needs of the people has always been a challenge to achieve. The existing E-Voting System (E-VS) is not that much compatible with that of the current trends and does not assure to provide more security A lot of distributed ledger technologies which has been an exciting approach during existing election voting process. If we take a look on the ways of implying E-VS in a distribute ledger then Blockchain would be the right choice. As we all know that nowadays, Blockchain is one of the emerging technologies in the field of Information Technology. It normally stores information in batches called blocks which are linked together in a chronological way or method to form chain of blocks using cryptography techniques. During online voting process, many fraudulent activities happens which corrupt the entire election process. One of the major problems faced are fake voting which is obviously done by unauthorized people, inconvenient to reach to the respective places, average security level which may lead to the chances of an electoral fraud or any other malpractices.. Our proposed E-Voting System is mainly to protect the cloud database for real time data and to reduce the time consumption in voting and vote counting processes. Instead of standing in the queue for casting the vote, people can cast their votes from anywhere they want through online. The E-VS gives complete privacy and security for the online voting and makes it an ease for every individual to access it and cast their votes from anywhere possible with full pronounced security. In our proposed E-VS, Blockchain security concept called Consensus algorithm is implemented which makes it impossible for any unwanted activities to occur during election process. The E-VS system also achieves a higher level of security. Hence, the proposed system achieves data integrity, data confidentiality, eliminates storage overhead, and reduces time consumption for overall electronic voting system.