Article
Physics, Multidisciplinary
Mingdong Liu, Hu Chen, Jiaqi Yan
Summary: The study introduces a goal-oriented approach to modeling, discovering, and analyzing different types of roles in agent-based business processes of bitcoin mixing scenarios using historical bitcoin transaction data. It focuses on investigating roles in the bitcoin money laundering process from the agents' goal perspective, and provides a foundation for identifying real-world agents' roles in bitcoin money laundering scenarios.
FRONTIERS IN PHYSICS
(2021)
Article
Business, Finance
Anantha Divakaruni, Peter Zimmerman
Summary: The Lightning Network allows for Bitcoin payments to be made off the blockchain, resulting in reduced congestion and increased efficiency. Our study reveals that this improvement cannot be accounted for by other factors and the impact of centralization on efficiency remains inconclusive. These findings have implications for the future of cryptocurrencies as a payment method and their environmental impact.
FINANCE RESEARCH LETTERS
(2023)
Article
Computer Science, Theory & Methods
Abdul Khalique Shaikh, Malik Al-Shamli, Amril Nazir
Summary: This paper discusses the importance of anti-money laundering policies for the stability of a country's economy and political system, as well as various technical solutions proposed in the current literature to control money laundering activities. It also proposes a model based on social network analysis to identify relationships between suspicious customers, aiming to prevent money laundering and potential terrorist financing activities.
JOURNAL OF BIG DATA
(2021)
Article
Management
Clynton Tomacheski, Anolan Milanes, Sebastian Urrutia
Summary: This work investigates the nilcatenation problem, a combinatorial optimization problem in graphs, and its potential application for detecting money laundering activities in cryptocurrency networks. It proposes a 0/1 integer linear programming formulation and a local branching algorithm to find a set of arcs that can be removed from a directed graph without changing the balance of any vertex. The approaches are evaluated using three sets of test instances from Bitcoin's testnet and mainnet networks, and experiments show the possibility of detecting artificially introduced and large nilcatenations in these networks, potentially indicating money laundering activities.
INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH
(2023)
Article
Chemistry, Multidisciplinary
Jialin Song, Yijun Gu
Summary: In this paper, we use a deep learning framework and incorporate more characteristics of Bitcoin transactions to predict money laundering in Bitcoin transactions. We created a dataset with 46,045 Bitcoin transaction entities and 319,311 associated Bitcoin wallet addresses. By aggregating this information into a heterogeneous graph dataset and proposing three metapath representations, we enrich the characteristics of Bitcoin transactions. The experimental results show that our framework significantly improves the accuracy of recognizing illicit Bitcoin transactions compared to traditional methods, making it more conducive to detecting money laundering activities in Bitcoin transactions.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Federico Franzoni, Xavier Salleras, Vanesa Daza
Summary: The Bitcoin P2P network protocol has become a reference model for modern cryptocurrencies, but topology obfuscation is not an effective countermeasure against network-level attacks. Research suggests that the benefits of an open topology may outweigh the risks, leading to the proposal of a protocol to reliably infer and monitor connections among reachable nodes in the Bitcoin network.
PEER-TO-PEER NETWORKING AND APPLICATIONS
(2022)
Article
Economics
Carmela D'Avino
Summary: Using a novel dataset, this paper explores the link between cross-border flows of illicit money and anti-money laundering (AML) regulatory and judicial system regimes. The results indicate the crucial role played by judicial system performance variables in explaining the layering phase patterns observed in the underlying data.
EUROPEAN JOURNAL OF LAW AND ECONOMICS
(2023)
Article
Computer Science, Artificial Intelligence
Ismail Alarab, Simant Prakoonwit
Summary: This study develops a classification model that combines long-short-term memory with graph convolutional network (GCN) to classify illicit transactions in the Elliptic data. It also introduces an active learning framework applied to the large-scale Bitcoin transaction graph dataset and evaluates the performance of different acquisition functions. The main finding is that the temporal-GCN model achieved significant success compared to previous studies, and the performance of acquisition functions was evaluated using Monte-Carlo based adversarial attack and dropout.
NEURAL PROCESSING LETTERS
(2023)
Article
Mathematics, Interdisciplinary Applications
Oscar M. Granados, Andres Vargas
Summary: This paper evaluates the money laundering mechanism in financial networks, studying the structure of some suspicious money laundering groups and how they can be detected using topological and geometrical considerations.
Article
Criminology & Penology
Mirko Nazzari
Summary: This study analyzes the money laundering activities of the Conti ransomware group and finds that the offenders are not sophisticated in laundering their illicit proceeds. They primarily transact with a single entity and concentrate most of the illegal assets in one service. Exchanges and dark web services are the preferred destinations.
TRENDS IN ORGANIZED CRIME
(2023)
Article
Computer Science, Hardware & Architecture
Kailun Yan, Jilian Zhang, Yongdong Wu
Summary: This paper discusses the issue of message propagation in the Bitcoin network and proposes a novel P2P network structure called LCN to address this problem. Experimental results show that LCN can significantly reduce message redundancy, improve message propagation speed, and maintain good robustness even in highly connected networks.
Article
Mathematics
Chaopeng Guo, Sijia Zhang, Pengyi Zhang, Mohammed Alkubati, Jie Song
Summary: The decentralization and anonymity of blockchain have attracted significant attention, but there has been an increase in blockchain money laundering incidents. Anti-money laundering efforts are crucial in the blockchain space. This article proposes LB-GLAT, a novel network that effectively captures the structure and attributes of money laundering on the blockchain transaction graph. Experiments show that LB-GLAT outperforms other methods in terms of accuracy, precision, recall, F1-score, and AUC.
Article
Computer Science, Information Systems
Guangyi Yang, Xiaoxing Liu, Beixin Li
Summary: As AML protocols and technologies strengthen, traditional laundering methods face scrutiny. Virtual currencies become more attractive for laundering due to their immunity from seizure and elusive traceability. This study introduces a twotier algorithm that uses heuristic rules and integrated learning to detect virtual currency money laundering. The algorithm combines statistical risk attributes and machine learning models to identify anomalous laundering patterns. This approach improves the accuracy of unsupervised learning methods for money laundering detection. Copyright © 2023 Elsevier Ltd.
COMPUTERS & SECURITY
(2023)
Article
Mathematics, Interdisciplinary Applications
Peter Gerbrands, Brigitte Unger, Michael Getzner, Joras Ferwerda
Summary: This study investigates the impact of anti-money laundering policies on the behavior of money launderers and their networks. Using a unique dataset of dynamic networks, the research finds that after the announcement of the fourth EU anti-money laundering directive, money laundering networks increase their use of foreigners and corporate structures. Additionally, money launderers become more dominant in criminal clusters.
Article
Engineering, Multidisciplinary
Taotao Wang, Chonghe Zhao, Qing Yang, Shengli Zhang, Soung Chang Liew
Summary: This study introduces the Ethereum Network Analyzer (Ethna) that accurately probes and analyzes the P2P network of the Ethereum blockchain. Extensive experiments reveal that the Ethereum P2P network exhibits small-world network effects, and the degree of nodes follows a power-law distribution.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Information Systems
Yang Li, Zibin Zheng, Hong-Ning Dai, Raymond Chi-Wing Wong, Haoran Xie
Summary: This paper presents a profit-based deep architecture with the integration of reinforced data selector (PDA-RDS) to address the challenges in applying deep learning methods to enhance trend-following strategies. Experimental results demonstrate that PDA-RDS outperforms existing baseline methods on stock-market datasets.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2023)
Article
Agriculture, Dairy & Animal Science
Xin-Hui Wang, Qing Li, Zi-Bin Zheng, Xiao-Gao Diao, Li-Wen He, Wei Zhang
Summary: This study applied the Nutrient Requirements of Cashmere Goats to supplementary feeding for pregnant Inner Mongolian cashmere goats under grazing. The results showed that supplementation based on the feeding standard enhanced the production performance of pregnant goats. This is important for the healthy and precise nutrition and management of cashmere goats.
Article
Agriculture, Dairy & Animal Science
Shengjun Zhao, Shilong Zhou, Yuanqi Zhao, Jun Yang, Liangkang Lv, Zibin Zheng, Honghua Lu, Ying Ren
Summary: In this study, the chemical composition and rumen degradation characteristics of amaranth hay at four different growth stages were investigated. The results showed that the initial bloom stage (IS) exhibited superior chemical composition and rumen degradability compared to the other stages.
Article
Computer Science, Artificial Intelligence
Lingjun Zhao, Huakun Huang, Weizheng Wang, Zibin Zheng
Summary: Device-free localization (DFL) is an emerging technology in the Internet of Things (IoT) field that can locate targets without carrying any equipment. In this paper, a channel-dependent attention empowered residual network (CA-ResNet) is designed to extract underlying signal features for precise localization. Experimental results show that our proposed approach achieves high localization accuracy and strong robustness.
APPLIED SOFT COMPUTING
(2023)
Article
Economics
Dun Li, Dezhi Han, Zibin Zheng, Tien-Hsiung Weng, Kuan-Ching Li, Ming Li, Shaokang Cai
Summary: Short and Distort (S & D) is a prevalent price manipulation scheme in the futures trading market, especially in the context of Bitcoin futures. This article presents the first detailed empirical study on S & D, combining the analysis of available information and cryptocurrencies, proposing a problematic definition and discriminatory criteria for S & D in Bitcoin futures. Additionally, a model for real-time detection of S & D in perpetual and term contracts is developed, demonstrating higher accuracy and robustness compared to previous studies. The results highlight significant S & D manipulation in both perpetual and term contracts, with Binance exchange being relatively secure and Bittrex exchange being the most vulnerable to S & D.
COMPUTATIONAL ECONOMICS
(2023)
Article
Computer Science, Software Engineering
Peilin Zheng, Zibin Zheng, Liang Chen
Summary: Blockchain and blockchain-based decentralised applications have attracted increasing attention recently. Connecting to unreliable blockchain peers in public blockchain systems can result in resource waste and loss of cryptocurrencies. To address this, a Hybrid Blockchain Reliability Prediction model (H-BRP) is proposed to evaluate and predict the reliability of blockchain peers. Comprehensive experiments on 100 blockchain requesters and 200 blockchain peers demonstrate the effectiveness of the H-BRP model, with the implementation and dataset of 2,000,000 test cases released.
Article
Computer Science, Information Systems
Xinran Fang, Wei Feng, Yunfei Chen, Ning Ge, Yan Zhang
Summary: The sixth-generation (6G) network aims to integrate communication and sensing functions to improve efficiency and support novel applications. The MIMO technique plays a crucial role in balancing communication and sensing performance, but it also brings challenges in terms of cost, power consumption, and complexity. This survey discusses the application of MIMO in joint communication and sensing (JCAS), outlines its roles in wireless communication and radar sensing, and explores current advances and potential solutions.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Yunlong Lu, Bo Ai, Zhangdui Zhong, Yan Zhang
Summary: This article proposes the model of wireless computing power networks (WCPNs) and solves the problems encountered by conventional mobile edge computing systems in 6G networks. By jointly unifying the computing resources from end devices and MEC servers, and optimizing the allocation of computation and communication resources through a deep reinforcement learning (DRL) algorithm, the objective of minimizing execution latency and energy consumption is achieved. Numerical results show improvement in computation efficiency, convergence rate, and utility performance.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Xueqing Yang, Xin Guan, Ning Wang, Yongnan Liu, Huayang Wu, Yan Zhang
Summary: Smart grid integrates distributed energy resources and massive information to facilitate energy flow in industries. Accommodating renewable energy is crucial for achieving energy efficiency, but optimal policies are difficult to obtain due to intermittency. To capture renewable energy statuses for decision-making, heterogeneous information is collected by end devices in smart grid, posing challenges for existing algorithms. This article proposes a cloud-edge-end computing scheme to efficiently repair missing values and obtain optimal policies in two separate layers using deep learning and deep reinforcement learning algorithms. Simulations on a real power grid dataset demonstrate the effectiveness of the proposed fault-tolerant renewable energy accommodation algorithm.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Engineering, Multidisciplinary
Yunlong Song, Yaqiong Liu, Yan Zhang, Zhifu Li, Guochu Shou
Summary: This paper proposes a proximity detection scheme for dynamic road networks based on Mobile Edge Computing (MEC), and formulates the proximity detection problem as a nonlinear optimization problem. By using the SLSQP algorithm and DDPG algorithm, the computational time can be effectively reduced, and the computational time of the DDPG algorithm is two orders of magnitude lower than that of the SLSQP algorithm.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Wen Sun, Sijia Lian, Haibin Zhang, Yan Zhang
Summary: The sixth-generation (6G) wireless network aims to provide universal and reliable network access through effective inter-networking among space, air, and terrestrial networks, which poses significant challenges for dynamic network orchestration. Digital twin (DT) offers an alternative approach to real-time resource allocation by mapping and learning the complex network topology. However, establishing a digital twin on aerial networks is difficult due to limited energy capacity and insufficient computing power of unmanned aerial vehicles. In this paper, a lightweight DT empowered air-ground network architecture is proposed, where the modelling task is distributed to ground devices using federated learning, and a distributed incentive mechanism is designed to incentivize high-performance ground devices.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Hardware & Architecture
Shiyi Qi, Yaoxian Li, Cuiyun Gao, Xiaohong Su, Shuzheng Gao, Zibin Zheng, Chuanyi Liu
Summary: This study proposes a Transformer-based model, named DTrans, for learning to predict code changes. By incorporating dynamically relative position encoding in the multi-head attention of Transformer, DTrans can accurately generate patches and locate lines to change with higher accuracy compared to existing methods.
IEEE TRANSACTIONS ON RELIABILITY
(2023)
Article
Computer Science, Theory & Methods
Hui Dou, Lei Zhang, Yiwen Zhang, Pengfei Chen, Zibin Zheng
Summary: Big data processing frameworks like Spark often come with numerous configuration parameters that affect performance, and auto-tuning these parameters is a long-standing issue in academia and industry. In this paper, we propose a cost-efficient configuration auto-tuning approach called TurBO that integrates adaptive pseudo point mechanism and CASampling method to achieve fast configuration adjustment in big data frameworks. Experimental results show that TurBO outperforms three baseline approaches, OpenTuner, Bliss, and ResTune, by 2.24x, 2.29x, and 1.97x respectively in terms of tuning speed. Furthermore, TurBO consistently delivers positive cumulative performance gain in a simulated dynamic workload scenario, making it suitable for workload changes in big data applications.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2023)
Article
Computer Science, Cybernetics
Jieli Liu, Weilin Zheng, Dingyuan Lu, Jiajing Wu, Zibin Zheng
Summary: This article provides a data-driven decentralization analysis of EOSIO and proposes methods to detect abnormal voting behaviors. The study reveals the evolution of decentralization in EOSIO and highlights potential issues in the system. The findings offer important insights for the design and maintenance of other DPoS-based blockchains.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
Dun Li, Dezhi Han, Tien-Hsiung Weng, Zibin Zheng, Hongzhi Li, Kuan-Ching Li
Summary: Stablecoins have facilitated the growth of decentralized payments and the emergence of a new generation of payment systems using cryptocurrencies and Blockchain technology. However, the existing research lacks a comprehensive overview of Stablecoins that focuses on their full context, stabilization mechanisms, and payment applicability. This paper provides a thorough summary of the definition, current state, and ecosystem of Stablecoins. It discusses the system structure, stability mechanisms, and their applicability in payment scenarios. The study identifies asset-backed Stablecoins as the most efficient and widely used, while cryptocurrency-backed Stablecoins are more balanced in relation to the original concept. Algorithm-backed Stablecoins show significant potential for development but are hesitant due to the lack of collateral or deposit reserves, making them prone to collapse. The paper concludes by presenting possible future trends for Stablecoins.
COMPUTER STANDARDS & INTERFACES
(2024)