Due to the strong untraceability of mixing services, numerous criminals exploit these services to engage in illicit activities, posing a significant threat to the blockchain ecosystem. This paper addresses the challenge of linking transaction addresses in Tornado Cash, a popular mixing service on Ethereum. While existing state-of-the-art solutions like MixBroker attempt to address this problem, two fundamental limitations persist: insufficient utilization of neighbor information and neglect of address information asymmetry. To address these gaps, a novel framework termed “MixLinker” is proposed, which enhances neighbor information utilization and models information asymmetry. Specifically, a Normalized Adjusted Personal PageRank (NAPPR) module is designed to prioritize significant neighbor nodes while mitigating interference from super and irrelevant addresses. Additionally, tensors are employed to model transactions, capturing rich interaction features related to transaction attributes. Based on historical transaction sequences, Tensor Long Short-Term Memory (TLSTM) is used to obtain high-quality initial input features for the Graph Neural Network (GNN) module, enabling effective learning of nonlinear dynamics. To ensure symmetric output results and model asymmetric information, a temporal-aware symmetry classifier is constructed that leverages asymmetric information through permutation operations and an order-aware classifier. Extensive experiments demonstrate that MixLinker outperforms other methods, validating the effectiveness of the proposed approach and confirming the two underlying motivations.
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.
Federated Learning (FL) enables decentralized model training while ensuring data privacy between clients and the server, and is applicable in various domains such as healthcare, finance, and edge computing. Traditional FL approaches assume homogeneous model architectures across clients and servers, limiting their applicability in real-world scenarios where clients use diverse models. To address this, we introduce Feature Align-HFL, a novel framework designed for Heterogeneous Federated Learning (HFL) that aligns dissimilar models for effective knowledge sharing. Specifically, we demonstrate its application by aligning CNNs and U-Nets for a common classification task. By employing cosine similarity, Feature Align-HFL identifies and aligns common features across heterogeneous models. Experiments on the CIFAR-10 dataset show that CNN and adapted U-Net models achieved 90 percent and 86 percent accuracy, respectively, with feature map similarities reaching up to 96 percent. These results highlight the significant transferable knowledge between dissimilar architectures, indicating that Feature Align-HFL can effectively support knowledge sharing in heterogeneous FL settings.
As decentralized applications on permissionless blockchains are prevalent, more and more latency-sensitive usage scenarios emerged, where the lower the latency of sending and receiving messages, the better the chance of earning revenue. To reduce latency, we present Pioplat, a feasible, customizable, and low-cost latency reduction framework consisting of multiple relay nodes on different continents and at least one instrumented variant of a full node. The node selection strategy of Pioplat and the low-latency communication protocol offer an elastic way to reduce latency effectively. We demonstrate Pioplat's feasibility with an implementation running on five continents and show that Pioplat can significantly reduce the latency of receiving blocks/transactions and sending transactions, thus fulfilling the requirements of most latency-sensitive use cases. Furthermore, we provide the complete implementation of Pioplat to promote further research and allow people to apply the framework to more blockchain systems.
Bitcoin, launched in 2008 by Satoshi Nakamoto, established a new digital economy where value can be stored and transferred in a fully decentralized manner - alleviating the need for a central authority. This paper introduces a large scale dataset in the form of a transactions graph representing transactions between Bitcoin users along with a set of tasks and baselines. The graph includes 252 million nodes and 785 million edges, covering a time span of nearly 13 years of and 670 million transactions. Each node and edge is timestamped. As for supervised tasks we provide two labeled sets i. a 33,000 nodes based on entity type and ii. nearly 100,000 Bitcoin addresses labeled with an entity name and an entity type. This is the largest publicly available data set of bitcoin transactions designed to facilitate advanced research and exploration in this domain, overcoming the limitations of existing datasets. Various graph neural network models are trained to predict node labels, establishing a baseline for future research. In addition, several use cases are presented to demonstrate the dataset's applicability beyond Bitcoin analysis. Finally, all data and source code is made publicly available to enable reproducibility of the results.
The web3 applications have recently been growing, especially on the Ethereum platform, starting to become the target of scammers. The web3 scams, imitating the services provided by legitimate platforms, mimic regular activity to deceive users. The current phishing account detection tools utilize graph learning or sampling algorithms to obtain graph features. However, large-scale transaction networks with temporal attributes conform to a power-law distribution, posing challenges in detecting web3 scams. In this paper, we present ScamSweeper, a novel framework to identify web3 scams on Ethereum. Furthermore, we collect a large-scale transaction dataset consisting of web3 scams, phishing, and normal accounts. Our experiments indicate that ScamSweeper exceeds the state-of-the-art in detecting web3 scams.
Blockchain, as a decentralized, secure, programmable, traceable, and tamper-resistant distributed ledger technology, has witnessed rapid development in various fields in recent years. This paper addresses the need for rapid data retrieval on blockchain and proposes a block construction and retrieval algorithm based on hybrid indexing. The algorithm aims to alter the underlying structure of blocks by utilizing data structures such as Merkle trees, linked lists, and hashes to facilitate data retrieval. Building upon this, block construction and retrieval algorithms are introduced to ensure efficient retrieval of corresponding transactions, maintaining low time complexity.
Research on Bitcoin (BTC) transactions is a matter of interest for both economic and network science fields. Although this cryptocurrency is based on a decentralized system, making transaction details freely accessible, making raw blockchain data analyzable is not straightforward due to the Bitcoin protocol specificity and data richness. To address the need for an accessible dataset, we present ORBITAAL, the first comprehensive dataset based on temporal graph formalism. The dataset covers all Bitcoin transactions from January 2009 to January 2021. ORBITAAL provides temporal graph representations of entity-entity transaction networks, snapshots and stream graph. Each transaction value is given in Bitcoin and US dollar regarding daily-based conversion rate. This dataset also provides details on entities such as their global BTC balance and associated public addresses.
Togzhan Barakbayeva, Zhuo Cai, Amir Kafshdar Goharshady, Karaneh Keypoor
Correlated equilibria are a standard solution concept in game theory and generalize Nash equilibria. In a 2-player non-cooperative game in which player i has action set A_i, a correlated equilibrium is a self-enforcing probability distribution σ over A_1 * A_2. Specifically, when a strategy profile (s_1, s_2) in A_1 * A_2 is sampled according to σ, each player i can observe their own component s_i, but not the other player's component. Knowing s_i and σ, player i cannot increase their expected payoff by defecting and playing a strategy s'_i different from s_i. Correlated equilibria are ubiquitous and crucial in mechanism design, including in the design of blockchain-based protocols which aim to incentivize honest behavior. A correlated equilibrium depends on a centralized and impartial oracle, often called the ''external signal'' in game theory literature, to sample a strategy profile and disclose each player's component to them, while keeping the other player's component secret. However, there is currently no trustless method to achieve this on the blockchain without centralization or relying on trusted third-parties. In this work, we address this challenge and provide two novel protocols, one based on oblivious transfer and the other based on zkSNARKs to replace the public signal with a smart contract. We prove that our approaches are secure and provide the desired privacy properties of a correlated equilibrium, while also being efficient in terms of gas usage and thus affordable in practice.
Federated learning (FL), a decentralized machine learning approach, enables privacy-preserving and collaborative model training without centralizing sensitive data. It has been successfully applied in various domains, including e-commerce, healthcare, and finance. However, existing FL schemes often fail to address personalized task requirements, such as prior-itizing the accuracy of specific classes within a dataset. The recent surge in Artificial Intelligence Generated Content (AIGC) offers potential to meet these personalized requirements by augmenting the training data of specific classes with generative models. Nevertheless, integrating generative models with FL introduces challenges, such as non-compliant data, disorganized distributions, and limited computing power on edge devices. To address these challenges, we propose AIGC-augmented Federated Preference Learning (FPL), which focuses on training specific data classes, referred to as preference classes (PCs). To improve the quality of AI -generated data, we implement strategies such as pre-training and fine-tuning across various datasets. Additionally, we enhance FL efficiency through a client selection strategy that matches generated data tasks with suitable clients and an AIGC data distribution strategy that optimally allocates data where it is most needed. We validate the feasibility and effectiveness of AIGC-augmented FPL by conducting experiments on the MNIST and CIFAR-10 datasets from various perspectives.
With the prosperity of the blockchain and the DeFi ecosystem, money flow activities in the blockchains are becoming increasingly frequent, complex, and diverse. The Money Flow Graph (MFG) serves as the foundation for various behavioral analysis, malicious activity detection, and money flow tracing tasks. However, traditional graph databases face the issue of storage requirement and performance when analyzing large-scale MFGs. In this work, we presentMFGScope, a lightweight domain-specific framework designed for graph-based analysis on EVM-compatible blockchains, with extensive optimizations for storage efficiency and query performance. The prototype ofMFGScopefor the Ethereum network achieves the storage of over 3 billion transfers and 1.7 billion relevant transactions in a single instance with less than 450 GB of disk usage. The evaluation shows that for common tasks,MFGScopeis more than 30 times faster and requires 78% less storage space than the commonly used graph database Neo4j. For the applications ofMFGScope, we present several use cases based on the MFG which cannot be performed efficiently using traditional graph databases and report interesting findings. To engage the community, the prototype ofMFGScopefor the Ethereum blockchain with the complete dataset will be open source.
Recently, with the prevalent adoption of blockchain in the financial system, there has been an increasing of anomaly activities such as ponzi schemes, gambling and phishing fraud on Ethereum platforms, and an effective account classification method is urgently required. The existing account classification methods on Ethereum with high accuracy require a learning system to be trained with balanced datasets. However, the distribution of annotated labels for account identities published on third-party sites is relatively imbalanced. Therefore, in this paper, We propose a EthGAN framework which includes a high-dimensional node feature representation module and a few-shot account data augment module to improve the accuracy and robustness at imbalanced datasets. The high-dimensional node feature representation module captures features from statistical, temporal, and transaction structure, and the few-shot account data augmentation module based on generative adversarial network models generate few-shot samples to improve the diversity and representativeness of the training datasets. We conduct extensive experiments to evaluate the performance of our proposed EthGAN framework on real-world Ethereum transaction data. The average classification effect of our method is 10+% higher than that of existing methods. Experimental results demonstrate that our method outperforms state-of-the-art methods in Ethereum account classification.
Ethereum, as one of today's most active blockchain platforms, provides extensive data for academic interest, thanks to its transparency and has garnered broad academic interest. Many studies model Ethereum transaction records as graph structures and design models to analyze phishing address transaction features. However, they often neglect the deep network structure of transaction sub-calls and lack efficient random walk strategies for optimal subgraph sampling. Therefore, this study introduces PR-Graph2vec, a PageRank- based graph embedding algorithm that captures the topological features of network phishing attacks from both the contract and sub-call perspectives, thereby improving phishing address detection. We extracted all transactions labeled as phishing from the blockchain explorer EtherScan to build a transaction network graph. Then, by aggregating the features of transaction call types and account types, we performed in-depth feature mining on transaction sub-calls. Finally, we used PageRank for biased sampling, significantly reducing the graph size. Experimental results demonstrate that our proposed Ethereum phishing detection model, PR-Graph2vec, excels in practical applications, achieving 91.0% precision and an 86.9% F1-score.
Cheng Zhang, Yang Xu, Xiaowei Wu, En Wang · 6 authors
Decentralized federated learning (DFL) overcomes the single point of failure issue of centralized federated learning. Building upon DFL, blockchain-based federated learning (BFL) takes further strides in establishing trust, enhancing security, and fault tolerance. However, BFL based on the classical linear blockchain exhibits diminished training efficiency in heterogeneous environments and is limited by the performance bottleneck of blockchain. Recent solutions introduce the directed acyclic graph (DAG) blockchain to address these issues, yet they compromise the verifiability of BFL, struggle with handling outdated models, and have a slow convergence speed. In this paper, we propose TGFL, a decentralized federated learning framework based on the Tree-Graph blockchain. The underlying blockchain structure of TGFL is designed as a block-centered DAG to support verifiable and semi-asynchronous training. To facilitate fast convergence, we design a pivot chain generation algorithm that topologically sorts the semi-asynchronous training process, guiding participants in sampling appropriate models. The consensus mechanism, which is closely integrated with federated learning, ensures that the TGFL can effectively resist attacks on the model and the blockchain system. Extensive experiments in various settings demonstrate that TGFL can achieve better training efficiency and model accuracy compared to three baselines.
Cryptocurrencies have experienced a surge in popularity, paralleled by an increase in phishing scams exploiting their transactional networks. Therefore, detecting anomalous transactions in the complex structure of cryptocurrency transaction data and the imbalance between legitimate and fraudulent data is considered a very important task. To this end, we introduce a model specifically designed for scam detection within the Ethereum network, focusing on its capability to process long and complex transaction graphs. Our method, Deep Graph traversal based on Transformer for Scam Detection (DGTSD), employs the DeepWalk algorithm to traverse extensive graph structures and a Transformer-based classifier to analyze intricate node relationships within these graphs. The necessity for such an approach arises from the inherent complexity and vastness of Ethereum transaction data, which traditional techniques struggle to process effectively. DGTSD applies subgraph sampling to manage this complexity, targeting significant portions of the network for detailed analysis. Then, it leverages the multi-head attention mechanism of the Transformer model to effectively learn and analyze complex patterns and relationships within the Ethereum transaction graph to identify fraudulent activity more accurately. Our experiments with other models demonstrate the superiority of this model over traditional methods in performance, with an F1 score of 0.9354. By focusing on the challenging aspects of Ethereum’s transaction network, such as its size and intricate connections, DGTSD presents a robust solution for identifying fraudulent activities, significantly contributing to the enhancement of blockchain security.
The Elliptic dataset compiles a comprehensive history of Bitcoin transactions, integrating both anti-money laundering (AML) tags and distinct graph network features. Given the nature of the Bitcoin transaction network—a complex, weakly interconnected structure—leveraging graph analysis techniques for its study holds immense potential, especially in the realm of detecting illicit activities like hacking, drug trades, gambling, and more. A detailed examination of the Elliptic dataset, encompassing transaction amounts, frequencies, source and destination addresses, sheds light on the inherent structure and peculiarities of the Bitcoin transaction ecosystem. By conceptualizing this transactional landscape as a graph, a slew of analytical attributes emerge: node degree distribution, community architecture, centrality measures, and so forth. Such attributes pave the way for the creation of predictive models that can pinpoint and prognosticate potential unlawful trade actions. Several computational models have been employed on the Elliptic dataset, such as Logistic Regression (LR), Random Forest (RF), Multilayer Perceptrons (MLP), and Graph Convolutional Networks (GCN). The authors of this particular study delve into augmentations of the GCN model, juxtaposing the efficacy of the original GCN model against their enhanced algorithm within the context of the Elliptic dataset.
Utilizing graph analytics and learning has proven to be an effective method for exploring aspects of crypto economics such as network effects, decentralization, tokenomics, and fraud detection. However, the majority of existing research predominantly focuses on leading cryptocurrencies, namely Bitcoin (BTC) and Ethereum (ETH), overlooking the vast diversity among the more than 10,000 cryptocurrency projects. This oversight may result in skewed insights. In our paper, we aim to broaden the scope of investigation to encompass the entire spectrum of cryptocurrencies, examining various coins across their entire life cycles. Furthermore, we intend to pioneer advanced methodologies, including graph transfer learning and the innovative concept of "graph of graphs". By extending our research beyond the confines of BTC and ETH, our goal is to enhance the depth of our understanding of crypto economics and to advance the development of more intricate graph-based techniques.
Nitin Kumar, S. Mirdula, Pushpa Singh, T. Gayathri · 6 authors
The primary objective of this research is to comprehensively explore and analyze the dynamics of the Ethereum network using innovative methodologies and system architectures. The study aims to extract meaningful statistics from the Ethereum blockchain, focusing on account activity, popularity trends, and the distribution of transactions. Through rigorous data collection, robust query construction, and advanced analytical techniques, the research seeks to provide valuable insights into how the Ethereum network has evolved, particularly in the aftermath of the “crypto bubble explosion.” The overarching goal is to contribute to the understanding of Ethereum's structural patterns, user behaviors, and the impact of external factors on the network. The research has yielded significant results, unveiling key insights into Ethereum network dynamics. The data collection phase, facilitated by Google BigQuery, successfully captured and filtered relevant information from a specific block range post the “crypto bubble explosion.” The SQL queries, strategically designed for active account identification and popularity assessment, demonstrated efficiency and accuracy in handling the vast Ethereum dataset. The proposed system, introducing the novel methodology of “portation,” showcased its efficiency in extracting and interpreting Ethereum blockchain data using Google BigQuery. The system architecture, as illustrated in the diagram, proved to be a well-coordinated and dynamic framework, emphasizing the seamless flow of data and processes.
In Ethereum, the ledger exchanges messages along an underlying Peer-to-Peer (P2P) network to reach consistency. Understanding the underlying network topology of Ethereum is crucial for network optimization, security and scalability. However, the accurate discovery of Ethereum network topology is non-trivial due to its deliberately designed security mechanism. Consequently, existing measuring schemes cannot accurately infer the Ethereum network topology with a low cost. To address this challenge, we propose the Distributed Ethereum Network Analyzer (DEthna) tool, which can accurately and efficiently measure the Ethereum network topology. In DEthna, a novel parallel measurement model is proposed that can generate marked transactions to infer link connections based on the transaction replacement and propagation mechanism in Ethereum. Moreover, a workload offloading scheme is designed so that DEthna can be deployed on multiple distributed probing nodes so as to measure a large-scale Ethereum network at a low cost. We run DEthna on Goerli (the most popular Ethereum test network) to evaluate its capability in discovering network topology. The experimental results demonstrate that DEthna significantly outperforms the state-of-the-art baselines. Based on DEthna, we further analyze characteristics of the Ethereum network revealing that there exist more than 50% low-degree Ethereum nodes that weaken the network robustness.
Haojie Sun, Zhaowei Liu, Shenqiang Wang, Haiyang Wang
With Ethereum blockchain advancement, the Ethereum platform gathers numerous users. In this context, traditional phishing appears new fraud methods, resulting in significant losses. Currently, network embedding methods are considered effective solutions in the field of phishing detection. However, investigating existing Ethereum phishing node detection algorithms finds they are not optimal and still face two issues. Firstly, the Ethereum network's topology is unsatisfactory, with nodes exhibiting a long-tail distribution in their degree. Current technologies typically allow high-degree nodes to acquire high-quality embeddings, while low-degree nodes, constrained by limited structure, obtain embeddings of lower quality, significantly impacting the detection accuracy of downstream tasks. Secondly, different features of nodes will suffer losses during the fusion process, resulting in the final learned feature embedding being suboptimal. This paper presents an attention-based graphical representation learning approach (ABGRL) to address these problems. ABGRL extracts different feature information by means of multiple channels, and fuses the different feature information using adaptive attention convolution to select the feature information that has the greatest impact on the downstream task. Then the tail node feature information is enhanced by a self-supervised regression model with robust tail node embedding. Finally, the effectiveness of the proposed model was validated through extensive experiments.
Time-varying graphs are increasingly common in financial, social and biological data analysis applications. Feature extraction that efficiently encodes the complex structure of sparse, multi-layered, dynamic graphs presents computational and methodological challenges. In the past decade, topological data analysis has become a popular method of studying the shape of data. This is achieved by building an increasing sequence of simplicial complexes (called filtration) indexed by a scale parameter on top of the data to keep track of topological changes along with the filtration. This multi-scale summary, called persistence diagram (PD), is often vectorized to be used in machine learning algorithms. This paper introduces a topological approach to extract information on higher-order interactions encoded in persistence diagrams from graph data. Our framework has two main steps: first, we convert the graph into a higher-dimensional simplicial complex by adding structures such as triangles, tetrahedrons etc., and compute a PD using the so-called lower-star filtration which utilizes quantitative node attributes. Then, we vectorize the PD by averaging the associated Betti function over successive scale values of a one-dimensional grid using integration. A notable aspect of our procedure is that it avoids embedding a graph into a metric space. We show that the proposed vectorization summary is robust against input noise with respect to the $ L_1 $ 1-Wasserstein distance. In simulation studies, the proposed approach leads to improved change point detection rates and outperforms one of the state-of-the-art methods for anomaly detection in time-varying graphs. In real data application, our approach leads to up to a 20% gain in anomalous price prediction in the Ethereum cryptocurrency transaction network.