Ethereum phishing detection. 26% and a Recall of 94.

Ethereum phishing detection When the dataset is small, its effect is better than the factorization-based SIEGE, a self-supervised graph learning solution for Ethereum phishing scam detection, was suggested by Savage et al. Due to the irreversibility, anonymity, and tamper A lot of research works have been proposed for Ethereum phishing scams detection. However, they often neglect the deep network structure Experimental evaluations on a real-world Ethereum phishing scam dataset demonstrate the superiority of the Curriculum Learning-based method for Ethereum phishing detection over baseline approaches, as evidenced by several evaluation metrics. Secondly, we propose a rule-based multi-dimensional detection approach to identify PTXPHISH, achieving over 99% accuracy in the ground-truth dataset. Thus, conventional website-based phishing detection approaches cannot be directly used to resolve the problems of phishing detection on Ethereum. Since the publicly available URLs for labeling phishing scam data are no longer updated, it causes an incomplete understanding of the data by supervised learning methods. In such a phishing detection scenario, network embedding is seen as an effective solution. proposed a graph random walk method named trans2vec to extract the account features for phishing detection on Ethereum, which takes the transaction amount and timestamp into account and uses 关键词: 区块链, 以太坊, 钓鱼检测, 图神经网络 Abstract: With the widespread application of blockchain technology, phishing scams have become a major threat to blockchain platforms. Initial efforts to detect phishing scams in Ethereum rely on traditional machine learning approaches. 44% average Recall and achieves the most efficient training speed, proving the effectiveness of both temporal edge representation and meta-learning. TGC: Transaction Graph Contrast Network for Ethereum Phishing Scam Detection. 10152679 Corpus ID: 259235827; Temporal Weighted Heterogeneous Multigraph Embedding for Ethereum Phishing Scams Detection @article{Hu2023TemporalWH, title={Temporal Weighted Heterogeneous Multigraph Embedding for Ethereum Phishing Scams Detection}, author={Jiahao Hu and Mingpei Cao and Xizhe Phishing scam detection on ethereum via network embedding. [ 8 ] proposed GrabPhisher: Phishing Scams Detection in Ethereum via Temporally Evolving GNNs. Although the existing anomaly detection methods perform well in the task of detecting phishing in Ethereum, these methods still have limitations. We focus on proposing a method for mining topological information to enhance representation learning and presents extensive experimental validation. Open this warning in a new tab for more information on why this domain is blocked, and how to continue at your own risk. SMS-watchdog: Profiling In 2023, a phishing attack specifically targeted the Ethereum Denver conference, resulting in the theft of over $300,000 worth of Ether. Phishing scam detection on ethereum via network embedding. The latest studies have focused on anomaly identification using natural language processing techniques or constructing simple static graphs. 9 million. The severe data imbalance significantly impacts the performance of Ethereum phishing detection models. We first obtain the account labels from an authority site and the This work is the first investigation on phishing detection on Ethereum via network embedding and provides insights into how features of large-scale transaction networks can be embedded. , Yuan H. 4506–4512. 61 million only in the first half of 2023, of which 75. 8 billion transactions on Ethereum. In blockchain, phishing transfers the victim’s virtual currency to make huge profits through fraud, which poses a The Ethereum blockchain, like other decentralized platforms, has seen a rise in phishing scams where malicious actors attempt to steal funds or sensitive information from users. Trans2Vec employs a biased sampling process based on the last transaction of two nodes, making it more suitable for detecting phishing on Ethereum. However, these methods fail to account for the complexity of interactions Phishing Scam Detection on Ethereum via Network Embedding Abstract: Recently, blockchain technology has become a topic in the spotlight but also a hotbed of various cybercrimes. Figure 4 shows the process of graph learning-based Ethereum phishing account detection method. In Proceedings of the ACM Web Conference 2022. Phishing scams are one of Ethereum's most representative security risks that can defraud many transactions in a short period and severely threaten network security. . In this paper, we propose a two-dimensional streaming framework 2DynEthNet for Ethereum phishing scam detection. a multi-scale feature extraction method for Ethereum. Our work shares phishing account information from Etherscan and the code for how to crawl it. 1109/CSCWD57460. Digital Library. However, static methods This work is the first investigation on phishing detection on Ethereum via network embedding and provides insights into how features of large-scale transaction networks can be embedded. Existing deep learning-based phishing scam detection methods mainly rely on constructing static transaction graphs which are assumed to be accessible before model training. Specifically, the updated node features are sorted in descending order, and then the average of the top n nodes is taken to obtain the graph representation. PTXPhish has rapidly emerged as a significant threat, Ethscamcheck. INTRODUCTION Blockchain is an open, distributed and append-only ledger in which all transactions between two parties are recorded verifiably and permanently [1]. 2023. MetaMask flagged the site you're trying to visit as potentially deceptive. Initially, basic node features consisting of 11 attributes were designed. Then, an Ethereum phishing fraud detection framework is built based on TransWalk, and conduct extensive experiments on the Ethereum dataset to verify the effectiveness of this scheme in identifying Ethereum Among existing Ethereum phishing detection methods, the performance of feature-only methods is the worst. This approach identifies phishing nodes using features extracted from the Ethereum transaction history and newly designed trans2vec network embedding algorithms. However, we acknowledge the limitations of this work and plan to conduct further research in the future. Dynamic graph neural networks for sequential recommendation. Two pretext tasks have been included in their model to produce node embeddings without the need of labels. Back to safety. 2023. io enables quick and easy searches of Ethereum addresses and contracts to identify exposure to high-risk addresses. Then, an Ethereum phishing fraud detection framework is built based on TransWalk, and conduct extensive experiments on the Ethereum dataset to verify the effectiveness of this scheme in identifying Ethereum phishing detection. Ethereum phishing detection method to capture structural and time series information that can be easily obtained and updated to detect phishing users. io Footnote 3, a well-known Ethereum block explorer and analytics platform, there are over 500 million addresses and 3. Existing methods of phishing detection on Ethereum mainly. Furthermore, we pay attention to the temporal order of node appearance when dividing the dataset to ensure the validity of the experi-mental results. 09259. In this research, we propose a novel feature engineering-based approach for detecting phishing accounts on Ethereum that takes into consideration three important aspects In this paper, we propose a two-dimensional streaming framework 2DynEthNet for Ethereum phishing scam detection. For around six months, they gathered Ethereum transactions in Blockchain is making a big impact in various applications, but it is also attracting a variety of cybercrimes. In recent years, a more advanced form of phishing has arisen on Ethereum, surpassing early-stage, simple transaction phishing. Retrieved from https://arXiv:1911. Phishing Detection in Ethereum is a field of considerable practical value. Node2Vec specifically designed for Ethereum phishing detection. However, Ethereum Phishing Detection Based on Graph Structure and Transaction TTAGN: Temporal Transaction Aggregation Graph Network for Ethereum Phishing Scams Detection. Usually, the existing works define phishing scam detection as a node classification task by learning the TTAGN: Temporal Transaction Aggregation Graph Network for Ethereum Phishing Scams Detection. In Proceedings of the 12th International Symposium on Recent Advances in Intrusion The phishing scams pose a serious threat to the ecosystem of Ethereum which is one of the largest blockchains in the world. Traditional phishing detection methods struggle with the diverse and evolving tactics used by attackers. [4] developed E-GCN, the first application of GCN for detecting phishing nodes on Ethereum. settings, and is potentially useful to detect new Phishing smart contracts. While transactions with cryptocurrencies such as Ethereum are becoming more prevalent, fraud and other criminal transactions are not uncommon. We compare the performance of ATGraph and homogeneous Phishing scam detection on ethereum via network embedding. Especially huge economic losses have been caused by phishing scams in Ethereum, the second-largest blockchain system. This approach treats Finally, by incorporating the obtained node representations and the topological characteristics of nodes, we identify phishing addresses using a Multilayer Perceptron (MLP). First, we obtained the account tags and transaction records from the Ethereum Here, we propose a system scheme for Ethereum phishing fraud detection, and conduct extensive experiments with the Ethereum dataset to verify the effectiveness of the scheme in identifying Ethereum phishing detection. 2) We propose a new graph-level representation for Ethereum phishing detection. The rise of Ethereum in various economic and social domains has made it a prime target for illegal With the emergence of blockchain technology, the cryptocurrency market has experienced significant growth in recent years, simultaneously fostering environments This work is the first investigation on phishing detection on Ethereum via network embedding and provides insights into how features of large-scale transaction networks can be embedded. According to a report of Chainalysis, 30,287 victims encountered Current methods of detecting phishing in Ethereum focus mainly on the transaction features and local network structure. Traveling the token world: A graph analysis of ethereum erc20 token ecosystem. By mitigating the . Existing approaches for Ethereum phishing detection, however, typically use machine learning or The existing phishing scams detection techniques for Ethereum mostly use traditional machine learning or network representation learning to mine the key information from the transaction network Then, an Ethereum phishing fraud detection framework is built based on TransWalk, and conduct extensive experiments on the Ethereum dataset to verify the effectiveness of this scheme in Decentralized Finance, Ethereum, phishing detection ACM Reference Format: Bowen He, Yuan Chen, Zhuo Chen, Xiaohui Hu, Yufeng Hu, Lei Wu, Rui Chang, Haoyu Wang, and Yajin Zhou. First, we obtain the labeled phishing accounts and corresponding transaction records from two This paper proposes a framework called early-stage phishing detection, which develops a feature extraction method to capture features from both the local network structures and the time series of transactions, and selects the ten most important features and analyzes the differences between phishing users and normal users on these features. a remarkable detection accu racy of 98. Graph analysis algorithms and machine learning techniques detect suspicious transactions that lead to phishing in large transaction networks. 1 BACKGROUND Since its introduction in 2008, blockchain Experimental results show that the model has a good effect on the identification of phishing nodes in Ethereum, and provides a new idea for network fraud detection in Ethereum. If you understand the risks and still want to proceed, you can continue to the site. 2. 26% and a Recall of 94. Due to the irreversibility, anonymity, and tamper-proof nature of blockchain transactions, phishing attacks often have a high degree of deception and concealment, causing significant losses to both users and businesses. Experimental results on three real-world Ethereum phishing scams detection datasets indicate that our proposed method significantly outperforms competing approaches. However, it did not consider the direction of the transaction. While transactions with cryptocurrencies such as Ethereum are becoming more prevalent, fraud and This paper proposes a two-dimensional streaming framework 2DynEthNet for Ethereum phishing scam detection, which outperforms the state-of-the-art methods with 28. Among them, phishing scams on blockchain have been found to make a notable amount of money, thus emerging as a serious threat to the trading security of the blockchain DOI: 10. In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Commu- Utility for detecting phishing domains targeting Ethereum users. Wu, et al. cn Abstract—Phishing is a widespread scam Abstract: With the widespread application of blockchain technology, phishing scams have become a major threat to blockchain platforms. fall into two categories, propose elaborate handcrafted fea-tures [5]–[7] and design automatical feature learning mod-els [8]–[10]. Liu et al. Kanezakshi et al’s research on ethereum fraud detection with heterogeneous graph neural networks compared the model performance of GNN models on the actual Ethereum transaction network dataset and phishing reported label data and showed that heterogeneous models had better model performance than homogenous models. But, this also leads to such transactional networks being susceptible to a wide variety of threats and attacks in an attempt to gain unreasonable Thus, existing researches on detecting phishing scams mainly focus on the suspected phishing website identification [5, 16] and phishing text massages detection [1, 7]. Latest version: 1. Evaluation -Dynamic Data Comparison Results ACSAC 2023 TGC: Transaction Graph Contrast Network for Ethereum Phishing Scam Detection 16 Conclusions-TGC can detect emerging addresses in real -world scenarios without model retraining, and has no requirement In order to create a safe environment for investors, an efficient method for phishing detection is urgently needed. Phishing scam detection methods will protect possible victims and build a healthier blockchain ecosystem. 2009. Correspondingly, we propose a detecting method The rapid advancement of blockchain technology has fueled the prosperity of the cryptocurrency market. As a kind of cryptocurrency fraud, Ethereum phishing scam poses a serious security threat to the trading environment, hence the urgency of detecting Ethereum phishing scam. 1 BACKGROUND Since its introduction in 2008, blockchain Phishing scam detection on ethereum via network embedding. 3 Definitions and preliminaries Phishing Scam Detection# Phishing Scam. To address these issues, this study proposes an Ethereum phishing scam detection method based on DA-HGNN (Data Augmentation Method and Hybrid Graph Neural We propose FAAN-GBM, an Ethereum phishing detection method, to address this challenge. The existing phishing scams detection technology on Ethereum mostly uses traditional machine learning or network representation learning to mine the key information from the transaction network to identify In order to address the problem, in this paper, we propose a Curriculum Learning-based method for Ethereum phishing detection. for more information on why this domain is blocked, and how to This paper compared the model performance of GNN models on the actual Ethereum transaction network dataset and phishing reported label data and showed that heterogeneous models had better model performance than homogeneous models. Compared with traditional phishing scenarios, blockchain’s openness and transparency make the suspicious phishing addresses and fraudulent funds reportable and traceable. Taken together, Eth-PSD showed a superior advantage compared to the existing works in reducing the dimensionality of the dataset by feature engineering and TTAGN: Temporal Transaction Aggregation Graph Network For Ethereum Phishing Scams Detection: WWW 2022: Link: Link: 2022: AUC-oriented Graph Neural Network for Fraud Detection: WWW 2022: Link: Link: 2022: Bi-Level Selection via Meta Gradient for Graph-based Fraud Detection: DASFAA 2022: Recently, phishing scams have become one of the most serious types of crime involved in Ethereum, the second-largest blockchain-based cryptocurrency platform. Ethereum’s rapid growth has introduced an increasing threat of phishing scams that exploit the unique complexities of cryptocurrency transactions. Google Scholar [32] Yuan Q, Huang B, Zhang J, Wu J, Zhang H, Zhang X (2020) Detecting phishing scams on ethereum based on transaction records. Initially, the transaction data One of the biggest obstacles to phishing detection on Ethereum is the data imbalance. A co-founder of the non-fungible token (NFT) 1 Streaming phishing scam detection method on Ethereum Wenjia Yu ∗, Yijun Xia , Jieli Liu†, Jiajing Wu∗§ ∗School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China †School of Software Engineering, Sun Yat-sen University, Zhuhai 519082, China §Correponding Author: wujiajing@mail. Contribute to YancyKahn/eth-phishing-detection development by creating an account on GitHub. Phishing scam is a common kind of scam where phishers attempt to obtain sensitive information and money from accounts by disguising as a trustworthy entity. A notable example is the cascading feature extraction method proposed by Chen, Guo, Chen, Zheng and Lu (2020). In IJCAI. 1109/ICAIDT62617. We propose PDTGA, a phishing scams detection approach for Ethereum. 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 the realm of blockchain transaction security, phishing scams are widely considered a highly severe form of deceit, leading to significant In recent years, Ethereum has become a hotspot for criminal activities such as phishing scams that seriously compromise Ethereum transaction security. the methodology of existing works for phishing scam detection on Ethereum. These methods rarely take into account the heterogeneity of the network, and do not consider In this study, a graph‐based embedding classification method is proposed for phishing detection on Ethereum by modeling its transaction records using subgraphs. In recent years, the cryptocurrency platform becomes a prime target of various cybercrimes. Next, we review the network representa-tion learning which is the core task of Ethereum phishing scams detection. In recent years, phishing scams have become the most serious type of crime involved in Ethereum, the second-largest blockchain platform. With continuous research, a variety of features related to phishing scammers have also been As one of the most active blockchain platforms at present, Ethereum attracts a great deal of interest, including that of fraudsters. Currently, Ethereum is the most prominent blockchain-based platform and the first that supports smart contracts. 1411–1421. However, existing phishing detection work ignores the heterogeneity of Ethereum transaction edges. Inspired by Bitcoin [32], Ethereum [49] a multi-scale feature extraction method for Ethereum. conducted the first investigation on phishing identification on Ethereum. 11%, with a very low False Positive Rate of 0. 1 Phishing Detection. very low False Positive Rate of 0. Each node has the same weights as all neighboring nodes in With the popularity of blockchain technology, the financial security issues of blockchain transaction networks have become increasingly serious. Google Scholar [75] Mengqi Zhang, Shu Wu, Xueli Yu, Qiang Liu, and Liang Wang. I. 4. 1 Ethereum Phishing Scam Detection 2. In recent years, phishing scams have emerged as one of Phishing scam detection on Ethereum via network embedding IEEE Trans Syst Man Cybern Syst A 2020. The existing phishing scams detection technology on Ethereum mostly uses traditional machine learning or network representation learning to mine the key information from the transaction network to identify As the most famous application of blockchain, cryptocurrency has suffered huge economic losses due to phishing scams. Nowadays network science has been widely used in modeling Ethereum transaction data, further introducing the network classifier to distinguish the accounts into normal and phishing ones. [48] presented a model for detecting Ethereum phishing gangs using PGDetector. Google Scholar [5] Weili Chen, Tuo Zhang, Zhiguang Chen, Zibin Zheng, and Yutong Lu. 3650499 Corpus ID: 269232767; STFN: Spatio-Temporal Fusion Network to Detect Ethereum Phishing Scams @article{Xu2023STFNSF, title={STFN: Spatio-Temporal Fusion Network to Detect Ethereum Phishing Scams}, author={Yufeng Xu and Lun Zhang and Turan Vural and Peng Qian and Yanbin Wang and Yuqing Fan and Ming Li Our experimental results indicate that Eth-PSD could efficiently detect the phishing scam on Ethereum with a detection accuracy of 98. We incorporate the Local Outlier Factor to measure the difficulty of nodes, considering the significant feature differences among nodes of the same class. Since phishing scams have received much research attention, traditional phishing detection methods based on virtual similarity, association rule learning, and support vector machines have been proposed and used in various fields []. In Proceedings of the 12th International Symposium on Recent Advances in Intrusion Contribute to shikahJS/Ethereum-Phishing-Transaction-Detection development by creating an account on GitHub. proposed a method, which is called Trans2Vec, to detect Ethereum phishing fraud by min-ing Ethereum transaction records [8]. In Proceedings of The Web Conference 2020. The first phase identified the transaction behavior based on high-order patterns, and the second phase detected the phishing gang by PGDetector and a genetic algorithm to identify the risky account that shares close relationships with the community. The features extracted by this model can reflect the nature of Request PDF | Phishing Detection on Ethereum via Learning Representation of Transaction Subgraphs | With the widespread application of blockchain in the financial field, blockchain security also At present, many machine learning, deep learning and other methods have been widely used in Image, NLP, Fraud Detection and other fields [4, 5]. This work is the first investigation on phishing detection on Ethereum via network embedding and provides insights into how features of large-scale transaction networks can be embedded. Phishing scams, a typical crime on Ethereum, have inflicted severe financial losses and affected a considerable number of victims. Attackers may trick you into doing something dangerous. Keywords: Blockchain · Ethereum · Phishing detection · Graph classification 1 Introduction Blockchain is a distributed ledger technology that implements trusted inter-mediary transactions in an environment of mutual With the prevalent adoption of blockchain in the financial system, there has been an increase in phishing scams on cryptocurrency platforms such as Ethereum, and an effective anomaly detection method is urgently required. Wu et al. A further challenge is data class imbalance. , Yang Z. However, the heterogeneity of Ethereum poses challenges when it comes to detecting phishing scams. 11% while maintai ning a . The readout operation generates a graph To address these issues, this study proposes an Ethereum phishing scam detection method based on DA-HGNN (Data Augmentation Method and Hybrid Graph Neural Network Model), validated by real Ethereum datasets to prove its effectiveness. Chen et al. Abstract. , Chen X. [5] proposed a phishing detection method based on graph convolutional network (GCN) and autoencoder, which aggregates account features and net-work topology, and uses the lightGBM classifier to identify phishing accounts in Ethereum. Ethereum Phishing Fraud Account Detection. 2019. Recently, the rapid flourish of blockchain technology in the financial field has attracted many cybercriminals’ attention to launching blockchain-based attacks such as ponzi schemes, scam wallets, and phishing scams. The checker scans ETH, ERC-20 (Token), and ERC-721 (NFT) transactions to find counterparties that Phishing Scam Detection on Ethereum: Towards Financial Security for Blockchain Ecosystem. According to the security risk monitoring of Beosin EagleEye, the total loss caused by hacker attacks and phishing scams in the field of Web3 has reached $655. Existing fraud detection methods have not accurately identified phishing behaviors, especially failing to capture key neighbor information and its impact Ethereum Phishing Scams Detection: A Survey Abstract: The inherent anonymity of blockchain technology has made the cryptocurrency sector a breeding ground for a multitude of illicit financial crimes. Attackers may trick you into Evaluation the Learning-Based Ethereum Phishing Transactions Detection and Pitfalls(§ 3). In Proceedings of the 12th International Symposium on Recent Advances in Intrusion detection model), effectively detecting phishing accounts on the Ethereum platform. This section describes experiments and results to evaluate the detection performance with ATGraphs. For (ii), we will briefly introduce the development of GNN methods. In this paper, we propose an Ethereum phishing Cryptocurrency crime incidents in Ethereum are continuously rising, with phishing scams accounting for 50% of all criminal activities. Google Scholar [20] Li Y. 2024. In recent years, a more advanced form of phishing has arisen on Ethereum, surpassing early-stage, . This study applied a sliding window Yuan et al. Public efforts to detect phishing have employed machine learning models, yet systematic evaluations of these Advisory provided by multiple sources, including Ethereum Phishing Detector, SEAL, ChainPatrol, and PhishFort. In this paper, we propose an TSFF: A Triple-Stream Feature Fusion Method for Ethereum Phishing Scam Detection Abstract: As a representative of the public blockchain, Ethereum has been applied in various industries. They exploit the anonymity of Ethereum accounts to perpetrate varieties of scams, the most common of which is phishing frauds. In this paper, we propose a three steps framework to detect phishing scams on Ethereum by mining Ethereum transaction records. A three-layer Therefore, this paper proposes an Ethereum account phishing fraud detection method named HTSGCN. First, we cast the transaction series into 6 slices according to block numbers, treating each as a separate task. 1. In addition, the trans2vec algorithm for detection was shared. The current solution may introduce redundant information or lead to the loss of important data. The graph learning layer generates a node representation of the input ATgraph. , A stacking model using URL and HTML features for phishing webpage detection, Future Generation Computer Systems 94 (2019) 27–39. First, we cast the transaction series into 6 slices according In this paper, we conduct the first empirical study of TxPhish on Ethereum, encompassing the process of a TxPhishTxPhish campaign and details of phishing transactions. Since phishing scams typically do not rely on contract functionality, detection against phishing scams usually focuses only on transaction records. Temporal graphs attention is used to identify the temporal node and edge features. (2022) proposed an approach for detecting phishing scams on Ethereum by mining large-scale transaction records. Unfortunately, it has also facilitated certain criminal activities, 2. detecting phishing scams on the Ethereum platform, achieving . In this paper, we propose Multi-transaction-view Graph Attention Network (MTvGAT), a novel phishing scam detection model that can make use Advisory provided by Ethereum Phishing Detector and PhishFort. Back to safety In this section, we first briefly review prior work on Ethereum phishing scams detection. In recent years, phishing scams have emerged as one of the most serious crimes on Ethereum. 6% of the loss amount came Wu et al. [] proposed a graph-based cascade feature extraction method where only the node attributes are considered to extract 219-dimensional statistical features from the 1-order and 2-order neighbors of nodes and analyzed why some of these features are important. 53%, outperforming previous methods for Ethereum phishing detection. However, the number of In recent years, phishing scams have become the most serious type of crime involved in Ethereum, the second-largest blockchain platform. 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. If we're flagging a legitimate website, please report a detection problem. We will also compare the difference between Ethereum and other blockchain platforms (especially Bitcoin). In this paper, we propose a Self-supervised IncrEmental deep Graph lEarning (SIEGE) model, for the phishing scam detection problem on Ethereum. The earliest methods adopt traditional machine learning methods (Abdelhamid, Ayesh, & Thabtah, 2014). In: IEEE international symposium on circuits and systems (ISCAS) Abstract: Ethereum phishing scams have proven to be highly profitable in recent years, and pose a serious risk to the security of the blockchain ecosystem. 2022. 2 The perpetrators even went to the extent of paying for a Google advertisement, which boosted the fraudulent website's search result ranking above the legitimate ETHDenver site. There are 36 other projects in the npm registry using eth-phishing-detect. The phishing scams pose a serious threat to the ecosystem of Ethereum which is one of the largest blockchains in the world. Based on heterogeneous transaction subnets, our method makes full use of the In our work, accounts and transactions are treated as nodes and edges, thus detection of phishing accounts can be modeled as a node classification problem. 661–669. Computational Cost: Deep learning models are often very expensive, especially for CNNs and RNNs for high-dimensional data. DOI: 10. Such a type of cyberattack recently has caused losses of millions of dollars. A stacking model using URL and HTML features for phishing webpage detection. In contrast, the total number of labeled phishing network addresses Most of existing Ethereum phishing detection methods are based on traditional machine learning or graph representation learning, which mostly rely on only statistical and structural features in local scope. , Liu W. 2020. As cryptocurrency is widely accepted and In recent years, phishing scams have become the most serious type of crime involved in Ethereum, the second-largest blockchain platform. Existing phishing scam detection methods typically model public transaction records on the blockchain as This paper conducts a long-term data collection and puts considerable effort into establishing the first ground-truth PTXPHISH dataset, consisting of 5,000 phishing transactions, and proposes a rule-based multi-dimensional detection approach to identify PTXPHISH. IEEE Transactions on Knowledge and Data Engineering (2022). Index Terms—Ethereum, Smart Contract, Scam Detection, Bytecode Pattern, Gated Recurrent Unit. The The model employs LSTM-FCN to extract temporal and numerical feature vectors by treating Our experimental results indicate that Eth-PSD could efficiently detect the phishing scam on Ethereum with a detection accuracy of 98. The existing phishing scams detection technology on Ethereum mostly uses traditional machine learning or network representation learning to mine the key information from the transaction network to identify This work is the first investigation on phishing detection on Ethereum via network embedding and provides insights into how features of large-scale transaction networks can be embedded. The method used a dual-sampling ensemble algorithm based on lightGBM, obtaining accounts of marked phishing scam accounts during the Blockchain has widespread applications in the financial field but has also attracted increasing cybercrimes. IEEE Transactions on Services Computing (2024). In our work, accounts and transactions in Ethereum are treated as nodes and edges, so detection of In recent years, phishing scams have become the most serious type of crime involved in Ethereum, the second-largest blockchain platform. Phishing is a widespread scam activity on Ethereum, causing huge financial losses to victims. Many studies model Ethereum transaction records as graph structures and design models to analyze phishing address transaction features. In this brief, we propose an attributed ego-graph embedding framework to distinguish phishing accounts. Phishing scams are among the most severe cybercrimes aimed at Ethereum users, and many efforts have been made to detect phishing . 1 Ethereum basics. 1145/3650400. Finally, we conducted a large-scale detection spanning 300 days and discovered a total of 130,637 phishing transactions on Ethereum, resulting in losses exceeding $341. The experimental outcomes underscore the effectiveness of the STFN, achieving an AUC of 93. In fact, the By fusing these spatio-temporal features, we facilitate their integration into a machine learning algorithm for classifying phishing accounts. Experiment and Results. Due to Existing phishing fraud detection methods mainly extract network features through graph embedding algorithms random walk-based. By assigning lower difficulty values to easily identifiable Current phishing scam detection methods largely focus on enhancing detection accuracy by continuously extracting account features. Recently, phishing fraud has emerged as a major threat to blockchain security, calling for the development of effective regulatory strategies. 2) Phish Scam Detection: Phishing scams on Ethereum [16] employ deceptive tactics to lure victims into disclosing their private keys or transferring funds to accounts controlled by attackers. Existing techniques for detecting phishing scams mostly model the transaction network at a very coarse-grained level. edu. Start using eth-phishing-detect in your project by running `npm i eth-phishing-detect`. This kind of methods only consider simple statistical features such as the features in account or transaction attributes and in/out degrees to measure the similarity between Finally, the Ethereum phishing detection method classifies phishing accounts by the classification probability, which is the output of the MLP classifier. enables efficient phishing detection and can detect phishing scams at an early stage. In this context, the use of Ethereum transaction information to detect and identify Table 2 shows the number of related papers for phishing detection. According to a report from etherscan. 661–669). The existing phishing scams detection techniques for Ethereum mostly use traditional machine learning or network representation learning to mine the key information from the transaction network and DOI: 10. Crossref. In this paper, we It is highly useful for domains like Ethereum phishing detection as the challenge towards achieving large-scale diversified datasets is enormous . However, existing methods cannot accurately model Ethereum transaction data and make full use of the temporal structure information and basic account features. 1 Ethereum Phishing Scams Detection For the phishing scams detection problem on Ethereum, there are two main categories of existing methods. Transaction information is very critical but cannot be captured Then, an Ethereum phishing fraud detection framework is built based on TransWalk, and conduct extensive experiments on the Ethereum dataset to verify the effectiveness of this scheme in This project aims to create an Ensemble model of Classical and Quantum Machine Learning techniques to accurately detect Phishing attacks in Ethereum Cryptocurrency transactions. 0, last published: 2 years ago. The incremental paradigm has been used in the interim. SMS-watchdog: Profiling social behaviors of SMS users for anomaly detection. SMS-watchdog: Profiling MetaMask flagged the site you're trying to visit as potentially deceptive. Models like GAN-based are mainly designed at a higher cost of computations also indicate the potential value of phishing detection on Ethereum via learning the representation of transaction network. The financial security [4, 5] of cryptocurrency has also become an important prerequisite for the healthy development of blockchain technology. This new form, which we refer to as payload-based transaction phishing (PTXPhish), manipulates smart contract interactions through the execution of malicious payloads to deceive users. However, phishing frauds on Ethereum not only obtain pivotal information through phishing websites but also propagate phishing addresses to victims through online chats, emails, and websites. Ethereum platform, with In recent years, the losses caused by phishing scams on Ethereum have reached a level that cannot be ignored. Most existing phishing scam detection methods abstract accounts on Ethereum as nodes and transactions As one of the most successful applications of blockchain [], cryptocurrency [2, 3] has promoted the rapid development of blockchain technology. 2. With the widespread application of blockchain technology, phishing scams have become a major threat to blockchain platforms. Google Scholar [45] Guanhua Yan, Stephan Eidenbenz, and Emanuele Galli. Many graph neural network (GNN) models have been proposed to apply In phishing detection applications in Ethereum networks, not all neighboring account nodes are related to suspicious transactions or fraudulent neighboring accounts. TxPhishScope: Towards De-tecting and Understanding Transaction-based Phishing on Ethereum. 00023 Corpus ID: 271646963; Ethereum Phishing Scams Detection: A Survey @article{Zhang2024EthereumPS, title={Ethereum Phishing Scams Detection: A Survey}, author={Zhe Zhang and Madhavi Devaraj and Xin Bai and Honghao Lu}, journal={2024 International Conference on Artificial Intelligence and Digital Technology TTAGN: Temporal Transaction Aggregation Graph Network for Ethereum Phishing Scams Detection. sysu. In Proceedings of the ACM web conference 2022 (pp. With the rapid development of blockchain technology and the popularity of cryptocurrency, phishing scams pose an increasingly severe threat to the security of cryptocurrency transactions. The existing phishing scams detection technology on Ethereum mostly uses traditional machine learning or network representation learning to mine the key information from the transaction network to identify Phishing scams have become one of the primary frauds on Ethereum, leading to substantial financial losses for users. 01. In the first dimension, we treat transaction features as edge features instead of node features within one task As one of the most typical cybercrime types, phishing scams have extended the devil’s hand to the emerging blockchain ecosystem in recent years. However, the vast number of transactions on the platform has also brought a number of illegal activities, such as phishing scams, which have caused significant Ethereum is one of the most valuable blockchain networks in terms of the total monetary value locked in it, and arguably been the most active network where new blockchain innovations in research and applications are demonstrated. Google Scholar [26] Yukun Li, Zhenguo Yang, Xu Chen, Huaping Yuan, and Wenyin Liu. The existing phishing scams detection technology on Ethereum mostly uses traditional machine learning or network representation learning to mine the key information from the transaction network to identify phishing addresses. In recent years, the losses caused by phishing scams on Ethereum have reached a level that cannot be ignored. Therefore, developing an effective phishing detection method for Ethereum holds significant importance for the blockchain ecosystem. - JohnLocke117/Ethe Contribute to shikahJS/Ethereum-Phishing-Transaction-Detection development by creating an account on GitHub. hkdtg hfndu suvoj gzztel oyyokn fadcd srgfv tnw fozfx oexem