No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Detection of Money Laundering in Bitcoin Transactions
Abstract
Combating Money laundering through cryptocurrencies has become a more challenging task due to the inherent anonymity of cryptocurrency transactions and the absence of centralized control authorities to apply known defensive laws and policies such as Know Your Customer (KYC) and Know Your Business (KYB) measures. This has led to an increase in number of cybercrimes that involve cryptocurrency as a payment method for illicit acts and a way to hide sources of dirty money. Therefore, researchers have been discovering new anti-money laundry detection and prevention techniques to combat these cybercrimes. In this work, we present an efficient anti-money laundry system that analyzes the transactions of cryptocurrency to learn data patterns that can identify licit and illicit transactions. Our system utilizes known machine learning mechanisms such as shallow neural networks and decision trees to construct the classification models. Without loss of generality, we evaluate our system on a recent bitcoin anti-money laundry dataset, the elliptic dataset, and use the classification accuracy as a performance indicator. Our analysis shows that shallow neural networks and decision trees achieve classification accuracy capped at 89.9% and 93.4%, respectively.
... The authors used various features extracted from the transactional behavior, including the number of transactions, the transaction frequency, and the transaction value, to train the ML models. Al Badawi et al. in [28] proposed a framework for identifying money laundering in Bitcoin transactions. The proposed framework presented a promising approach for detecting potential money laundering activities in Bitcoin transactions using ML techniques, which could have important implications for improving security and transparency of the Bitcoin network and preventing illegal activities. ...
... However, a single algorithm may not provide accurate results and may not generalize well to new or unseen data. Additionally, the authors in [19], [28] developed an efficient system for detecting money laundering in cryptocurrency transactions using ML techniques like SNN and DT, but their classification accuracy decreases as input features increase and are prone to overfitting. ...
... LGBM algorithm may not be the best choice for small datasets, as it may lead to overfitting [8]. L2: As the number of input features increases, the classification accuracy of SNN and DT tends to decrease [28]. L3: The authors noted that a single algorithm may not be enough to provide accurate results. ...
Bitcoin has a reputation of being used for unlawful activities, such as money laundering, dark web transactions, and payments for ransomware in the context of smart cities. Blockchain technology prevents illegal transactions, but cannot detect these transactions. Anomaly detection is a fundamental technique for recognizing potential fraud. The heuristic and signature-based approaches were the foundation of earlier detection techniques, but tragically, these methods were insufficient to explore the entire complexity of anomaly detection. Machine Learning (ML) is a promising approach to anomaly detection, as it can be trained on large datasets of known malware samples to identify patterns and features of the transactions. Researchers are focusing on determining an efficient fraud and security threat detection model that overcomes the drawbacks of the existing methods. Therefore, ensemble learning can be applied to anomaly detection in Bitcoin by combining multiple ML classifiers. In the proposed model, the ADASYN-TL (Adaptive Synthetic + Tomek Link) balancing technique is used for data balancing. Random search, grid search and Bayesian optimization are used for hyperparameter tuning. The hyperparameters have a great impact on the performance of the model. For classification, we used the stacking model by combining Decision Tree, Naive Bayes, K-Nearest Neighbors, and Random Forest. We used SHapley Additive exPlanation (SHAP) to interpret the predictions of the stacking model. The model also explores the performance of different classifiers using accuracy, F1-score, Area Under Curve-Receiver Operating Characteristic (AUC-ROC), precision, recall, False Positive Rate (FPR) and execution time, and ultimately selects the ideal model. The proposed model contributes to the development of effective fraud detection models that address the limitations of the existing algorithms. Our stacking model, which combines the prediction of multiple classifiers, achieved the highest F1-score of 97%, precision of 96%, recall of 98%, accuracy of 97%, AUC-ROC of 99% and FPR of 3%.
... Badawi et al. [105] Thoroughly assessed two classifiers for detecting crypto money laundering and revealing complex data patterns. ...
... Badawi et al. [105] compared the performance of two well-known machine learning algorithms in detecting cryptocurrency antimoney laundering and learning data patterns. The compared machine learning algorithms (i.e., decision trees and shallow neural networks) were tested on the Elliptic dataset. ...
Web 3.0 marks the beginning of a new era for the internet, characterized by distributed technology that prioritizes data ownership and value expression. Web 3.0 aims to empower users by providing them with ownership and control of their data and digital assets rather than leaving them in the hands of large corporations. Web 3.0 relies on decentralization, which uses blockchain technology to ensure secure user communication. However, Web 3.0 still faces many security challenges that might affect its deployment and expose users’ data and digital assets to cybercriminals. This survey investigates the current evolution of Web 3.0, outlining its background, foundation, and application. This review presents an overview of cybersecurity risks that face a mature Web 3.0 application domain (i.e., decentralized finance (DeFi)) and classifies them into seven categories. Moreover, state-of-the-art methods for addressing these threats are investigated and categorized based on the associated security risks. Insights into the potential future directions of Web 3.0 security are also provided.
... • Decentralized: it means all data processes like storage, maintenance, verification, and sharing are based on distributed system structure, and the trust between these nodes is built by mathematical methods or puzzles rather than third-trusted parties [17]. ...
... Money laundering [17] is thought to be involved in 5% of all global GDP transactions, so the issue is only getting worse. Every year, illicit flows totaled close to $1 trillion. ...
Blockchain technology provides a data structure with intrinsic security qualities, such as cryptography, decentralization, and consensus, that guarantee the integrity of transactions. It has wide-ranging applications, including the Internet of Things (IoT), health, intelligent manufacturing, finance, and many more. In this chapter, we shed light on the blockchain solutions for cyber criminals, concepts, elements, structure, and other aspects of blockchain utilization. Specifically, this chapter extends the elaboration on the blockchain, the blockchain components, the blockchain architecture, features, types, and limitations. Also, this chapter will extend the elaboration on cyber criminals, their types, their security needs, blockchain solutions, issues, challenges, and difficulties of using blockchain technology to fight cyber crimes. This chapter deepens the knowledge of blockchain solutions for cyber criminals and provides more insights to readers about blockchain, cyber attacks, cyber criminals, and their countermeasures.
... The authors also proved that unsupervised learning models have poor performance in a similar environment. Badawi and Al-Haija, in [70], also used an elliptic dataset to build machine learning models to detect money laundering activities. This paper compared the performance of the neural network and decision tree models in detecting felonious activities. ...
... Clustering the data using an expectation-maximization algorithm to extract features to detect laundering with Random Forest by Baek et al., [71] has shown highly efficient performance with a F1 score of 92%. Badawi and Al-Haija's comparison of neural networks and decision trees has also performed well with F1 scores of 89.7% and 93.5%, respectively, in identifying money laundering [70]. Additionally, algorithms such as Extra Trees, Bagging, Ada Boost, and the ensemble method in [54] have done well, with F1 scores over 80%. ...
With the emergence of cryptocurrencies and Blockchain technology, the financial sector is turning its gaze toward this latest wave. The use of cryptocurrencies is becoming very common for multiple services. Food chains, network service providers, tech companies, grocery stores, and so many other services accept cryptocurrency as a mode of payment and give several incentives for people who pay using them. Despite this tremendous success, cryptocurrencies have opened the door to fraudulent activities such as Ponzi schemes, HYIPs (high-yield investment programs), money laundering, and much more, which has led to the loss of several millions of dollars. Over the decade, solutions using several machine learning algorithms have been proposed to detect these felonious activities. The objective of this paper is to survey these models, the datasets used, and the underlying technology. This study will identify highly efficient models, evaluate their performances, and compile the extracted features, which can serve as a benchmark for future research. Fraudulent activities and their characteristics have been exposed in this survey. We have identified the gaps in the existing models and propose improvement ideas that can detect scams early.
... In traditional economy systems, payments are processed exclusively by financial institutions like banks, regardless of their form (cash or electronic). These institutions act as intermediaries during fund transfers, thereby exercising complete control of the financial transaction as it works well for it, it restricts the amount of money that is transacted and lacks the necessary trust, security, transparency, and adaptability (Badawi & Al-Haija, 2021). To tackle these shortcomings, we desire a system that eliminates financial intermediaries, enabling direct money transfers between parties. ...
This paper investigates the efficacy of deep learning models such as Long-Short Term Memory (LSTM), Convolutional Neural Networks (CNN), and Gated Recurrent Units (GRU) for cryptocurrency price prediction, examining their short-term and long-term forecasting accuracy for investor guidance and advancing AI in financial analysis. The study uses time series analysis with LSTM, CNN, and GRU models on daily cryptocurrency prices from Investing.com, preprocessing data before testing on Bitcoin, Ethereum Classic, Ethereum, Litecoin, Monero, and the other 37 cryptocurrencies. RMSE, MAE, and accuracy rates measure performance. Findings revealed that only six cryptocurrencies were selected for final analysis, including Bitcoin, Ethereum Classic, Ethereum, Litecoin, and Monero. Results indicate that the deep learning models, particularly the LSTM and GRU, can predict cryptocurrency prices with high accuracy, especially for short-term forecasts within a 7-day window. The CNN model demonstrates significant predictive power, suggesting its utility for immediate trading decisions. Across the models, short-term precision was remarkably high, while long-term predictions maintained a moderate level of accuracy. This study presents a comparative analysis of LSTM, GRU, and CNN models for forecasting cryptocurrency prices, emphasizing LSTM and GRU's ability to navigate price volatility and suggesting their use for real-time trading analysis. The study's historical data reliance curtails forecasting unforeseen market shifts. Future studies should include new variables like social sentiment and blockchain analytics and test real-time adaptive models to enhance predictive strength. Model validation in actual market conditions is recommended for practical application.
... Cryptocurrencies like Bitcoin offer anonymity and decentralization, which makes it difficult to apply traditional financial regulations such as know your customers (KYC) and know your business (KYB) decisions. These characteristics has made cryptocurrencies attractive to cybercriminals due to money laundering and illegal storage of funds [4]. Bitcoin's decentralized and pseudonymous nature makes it an attractive option for cybercriminals seeking anonymity and ease of transfer. ...
This study tackles the critical issue of identifying ransomware transactions within the Bitcoin network. These transactions threaten the stability and security of the cryptocurrency world. Traditional machine learning methods struggle to adapt to the evolving tactics employed by ransomware attackers. They rely on predefined features and metrics, limiting their ability to replicate the adaptability of human analysts. To address this challenge and to address the dynamic nature of fraudulent Bitcoin transactions, we propose a novel approach that incorporates Deep Q-Network (DQN) with Boltzmann exploration model that can autonomously learn and identify evolving attack patterns. The proposed Deep Reinforcement Learning (DRL) offers a more flexible approach by mimicking how security experts learn and adjust their strategies. DQN is a type of reinforcement learning that allows the agent to learn through trial-and-error interactions with the environment. Boltzmann exploration is a technique used to balance exploration (trying new actions) and exploitation (taking actions with the highest expected reward) during the learning process. Proposed DQN model with Boltzmann exploration was evaluated in a simulated environment. This strategy emphasizes the importance of dynamic decision-making for achieving convergence and stability during the learning process, ultimately leading to optimized results. The model achieved a promising validation accuracy of 91% and a strong F1 score demonstrating its ability to generalize effectively to unseen data. This is crucial for real-world applications where encountering entirely new attack scenarios is likely. Compared to alternative exploration techniques like Epsilon-Greedy and Random Exploration, Boltzmann exploration led to superior performance on unseen data. This suggests that the Boltzmann temperature parameter effectively guided the agent’s exploration-exploitation trade-off, allowing it to discover valuable patterns applicable to new datasets. In conclusion, our findings demonstrate the potential of DQN with Boltzmann exploration for unsupervised ransomware transaction detection in the Bitcoin network. This approach offers a promising solution for improving the security and resilience of Bitcoin networks against evolving ransomware threats.
... Money laundering poses a critical threat to the integrity of global financial systems by masking the origins of illicit funds, enabling criminal activities, and injecting substantial unaccounted money into the economy [7,9,11]. This infiltration distorts financial stability and intensifies economic problems such as inflation [6,20]. As laundered money flows into various assets and markets, it causes unjustified price increases, disproportionately affecting middle-class individuals who rely on long-term savings. ...
Money laundering is a serious threat to global financial systems, causing instability and inflation, and especially hurting middle-class savings. This paper suggests a new way to tackle these problems by using blockchain technology and advanced machine learning models. We use hyperledger fabric to securely record transactions and advanced algorithms like autoencoders and neural networks to create a strong anti-money laundering (AML) system. This system can detect and predict illegal financial activities in real-time and includes continuous monitoring and alerts. These features improve financial transparency and stability while protecting the savings of the middle class. By identifying and reducing risks early, our solution not only ensures compliance with regulations but also strengthens the resilience of global financial systems against new threats. This research helps develop effective ways to fight financial crime, promoting a safer and more transparent financial world. Read the full text here (View-Only): https://rdcu.be/d2Nqx
... Conversely, encryption guarantees that payment-related data, especially financial card numbers and account information, is safely stored and communicated across the network [6]. Lastly, a successful payment method must contain risk management capabilities, including fraud detection and prevention, to detect and prevent suspicious activities such as money laundering [7]. This review article examines the technological underpinnings, benefits, problems, and prospects of secure mobile payment systems. ...
Mobile devices, in particular, have revolutionized how financial transactions are conducted, making secure mobile payment (SMP) a primary method for completing transactions. The intersection of finance and technology, facilitated by internet usage, has given rise to digital payment systems, which serve as the foundation for financial inclusion. However, the convenience of mobile payment also brings forth several security issues that need to be addressed. Near Field Communication (NFC) technology has significantly impacted consumers' lives by integrating with mobile payment systems. Consequently, NFC-enabled payment systems have recently emerged in the consumer market, attracting the interest of businesses seeking to invest in this technology. This study comprehensively examines the mobile payment security landscape, encompassing security challenges and proposed solutions. Through this review, we aim to contribute to understanding mobile payment security and foster advancements that ensure a secure and reliable payment ecosystem.
... Anomaly detection is an essential technique used to identify abnormal patterns that differ from the expected behaviour of various AI applications, such as computer vision, data mining, and Natural Language Processing (NLP). There are two basic types of anomaly transaction detection techniques: supervised and unsupervised, including Restricted Boltzmann Machines (RBM), Deep Boltzmann Machines (DBM), Denoising Autoencoders, Decision Trees [13], Bayesian networks, association rules, and support vector machines [15], among others. Blockchain technology has three categories: public chain, consortium chain, and private chain, with the first two being the most commonly used. ...
The anonymous and tamper‐proof nature of the blockchain poses significant challenges in auditing and regulating the behaviour and data on the chain. Criminal activities and anomalies are frequently changing, and fraudsters are devising new ways to evade detection. Moreover, the high volume and complexity of transactions and asymmetric errors make data classification more challenging. Also, class imbalances and high labelling costs are hindering the development of effective algorithms. In response to these issues, the authors present BlockDetective, a novel framework based on GCN that utilizes student–teacher architecture to detect fraudulent cryptocurrency transactions that are related to money laundering. The authors’ method leverages pre‐training and fine‐tuning, allowing the pre‐trained model (teacher) to adapt better to the new data distribution and enhance the prediction performance while teaching a new, light‐weight model (student) that provides abstract and top‐level information. The authors’ experimental results show that BlockDetective outperforms state‐of‐the‐art research methods by achieving top‐notch performance in detecting fraudulent transactions on the blockchain. This framework can assist regulators and auditors in detecting and preventing fraudulent activities on the blockchain, thereby promoting a more secure and transparent financial system.
... As of October 2020, there were 7378 cryptocurrencies, with a combined market capitalization of about 359.7 billion in USD [9]. Bitcoin is a Peer-to-Peer (P2P) payment cash system that allows internet payments to be transmitted directly from one to another without a need to go to a banking institution [10]. It was created in 2008 by Satoshi Nakamoto and became well-known in 2009. ...
Cryptocurrencies like Bitcoin are one of today's financial system’s most contentious and difficult technological advances. This study aims to evaluate the performance of three different Machine Learning (ML) algorithms, namely, the Support Vector Machines (SVM), the K Nearest Neighbor (KNN), and the Light Gradient Boosted Machine (LGBM), which seeks to accurately estimate the price movement of Bitcoin, Ethereum, and Litecoin. To test these algorithms, we used an existing continuous dataset extracted from Kaggle and coinmarketcap.com. We implemented models using the Knime platform. We used auto biner for volume and market capital. Sensitivity analysis was performed to match different parameters. The F and accuracy statistics were used for the evaluation of algorithm performances. Empirical findings reveal that the KNN has the highest fore-casting performance for the overall dataset in our first investigation phase. On the other hand, the SVM has the highest for forecasting Bitcoin and the LGBM for Ethereum and Litecoin in the individual dataset in the second investigation phase.
... This method collects information from the input and then employs the rules to decide to take the right path. For example, in [17], the authors have employed decision trees to recognize money laundering in bitcoin transactions with high accuracy and minimum inferencing time. neurons and the function of the human brain in composing related groups of artificial neurons jointly. ...
Anomaly detection techniques have attracted more attention in research and industrial areas. Anomaly detection methods have been implemented in many tenders, such as detecting malicious traffic in networks and systems, discovering vulnerabilities in security systems, detecting fraud transactions in credit cards, detecting anomalies in imaging processing, and analyzing and visualizing data in various domains. The IoT ecosystem involves applications like intelligent homes, smart cities, and smart transportation systems. With the increasing necessity for analyzing IoT network behavior, it becomes difficult to efficiently apply traditional anomaly detection techniques. The conventional techniques that use deep learning (DL) or machine learning (ML) do not detect or monitor the IoT ecosystem efficiently and effectively because they do not consider the nature of the IoT ecosystem. Another issue with traditional anomaly detection techniques is that they recalculate training whenever any change from the start points. Furthermore, they depend on a static threshold throughout the training period. This does not fit with the nature of the IoT ecosystem, which is characterized by a dynamic environment. This chapter will discuss the autonomous anomaly detection system for the Internet of Things (IoT) using ML. Specifically, we focus on the dynamic threshold that can be adapted during the training time, such as the local-global ratio technique (LGR) method, which activates the rehabilitating merely when it is essential and precludes any superfluous variations from immaterial differences in the local profiles.
... Indeed, it has been declared that over 500 types of ransomware attack can be launched against blockchain data; and thus, solutions are required to address the detection and classification problem for the different ransomware families [40]. For that reason, recently, researchers have devoted plenty of effort to developing identification and classification systems to detect, mitigate, and prevent such dangerous cyberattacks using machine and deep learning techniques [20,[41][42][43][44][45]. ...
The blockchain protocol is a digitally distributed system that records and verifies Bitcoin transactions, preserved by numerous distributed autonomous computers. The blockchain system is composed of multiple decentralized connected blocks (chains of blocks) that are managed using distributed ledger technology (DLT). Every block in the chain holds several transactions, and a new block is attached to the chain when a new transaction occurs. Their decentralized nature and architecture are what make blockchain systems robust, secure, and challenging to attack or cheat. Therefore, the blockchain system has gained significant attention from cybersecurity researchers/scholars who have applied this technology to address security concerns in various applications such as money laundering monitoring. In this chapter, we will first revisit and investigate the robust decentralized architecture of blockchain technology and the different features that correlate the blockchain system with various security applications. Then, we will consider the review for the current trends of blockchain security. Thereafter, we will consider the investigating of the security breaches paradigms of blockchain. Subsequently, we will navigate through several e-security services and blockchain technologies for improved IoT security applications and services.
... Next, fewer features were chosen so that features used in the gradient-descent assault could be removed. This reduces the attack's viability even further at the expense of the SVM's precision [38]. The authors also suggested employing adversarial learning to train the SVM using gradient-descent-forged PDF files and repeating the procedure to decrease the likelihood that the gradient-descent attack will succeed. ...
Portable document format (PDF) files are one of the most universally used file types. This has incentivized hackers to develop methods to use these normally innocent PDF files to create security threats via infection vector PDF files. This is usually realized by hiding embedded malicious code in the victims’ PDF documents to infect their machines. This, of course, results in PDF malware and requires techniques to identify benign files from malicious files. Research studies indicated that machine learning methods provide efficient detection techniques against such malware. In this paper, we present a new detection system that can analyze PDF documents in order to identify benign PDF files from malware PDF files. The proposed system makes use of the AdaBoost decision tree with optimal hyperparameters, which is trained and evaluated on a modern inclusive dataset, viz. Evasive-PDFMal2022. The investigational assessment demonstrates a lightweight and accurate PDF detection system, achieving a 98.84% prediction accuracy with a short prediction interval of 2.174 μSec. To this end, the proposed model outperforms other state-of-the-art models in the same study area. Hence, the proposed system can be effectively utilized to uncover PDF malware at a high detection performance and low detection overhead.
... Next, fewer features were chosen so that features used in the gradient-descent assault could be removed. This reduces the attack's viability even further at the expense of the SVM's precision [38]. The authors also suggested employing adversarial learning to train the SVM using gradient-descent-forged PDF files and repeating the procedure to decrease the likelihood that the gradient-descent attack will succeed. ...
Portable document format (PDF) files are one of the most universally used file types. This has incentivized hackers to develop methods to use these normally innocent PDF files to create security threats via infection vector PDF files. This is usually realized by hiding embedded malicious code in the victims’ PDF documents to infect their machines. This, of course, results in PDF malware and requires techniques to identify benign files from malicious files. Research studies indicated that machine learning methods provide efficient detection techniques against such malware. In this paper, we present a new detection system that can analyze PDF documents in order to identify benign PDF files from malware PDF files. The proposed system makes use of the AdaBoost decision tree with optimal hyperparameters, which is trained and evaluated on a modern inclusive dataset, viz. Evasive-PDFMal2022. The investigational assessment demonstrates a lightweight and accurate PDF detection system, achieving a 98.84% prediction accuracy with a short prediction interval of 2.174 μSec. To this end, the proposed model outperforms other state-of-the-art models in the same study area. Hence, the proposed system can be effectively utilized to uncover PDF malware at a high detection performance and low detection overhead.
... Next, fewer features were chosen so that features used in the gradient-descent assault could be removed. This reduces the attack's viability even further at the expense of the SVM's precision [38]. The authors also suggested employing adversarial learning to train the SVM using gradient-descent forged PDF files and repeating the procedure to decrease the likelihood that the gradient descent attack will succeed. ...
Portable Document Format (PDF) files are one of the most universally used file types. This has fascinated hackers to develop methods to use these normally innocent PDF files to create security threats via infection vectors PDF files. This is usually realized by hiding embedded malicious code in the victims’ PDF documents to infect their machines. This, of course, results in PDF Malware and requires techniques to identify benign files from malicious files. Research studies indicated that machine-learning methods provide efficient detection techniques against such malware. In this paper, we present a new detection system that can analyze PDF documents in order to identify benign PFD files from malware PFD files. The proposed system makes use of the AdaBoost decision tree with optimal hyperparameters, which is trained and evaluated on a modern-inclusive dataset, viz. Evasive-PDFMal2022. The investigational assessment demonstrates a lightweight-accurate PDF detection system, achieving a 98.84% prediction accuracy with a short prediction interval of 2.174 μSec. To this end, the proposed model outperforms other state-of-the-art models in the same study area. Hence, the proposed system can be effectively utilized to uncover PDF malware at high detection performance and low detection overhead.
... Despite their positive results, the authors were openly doubtful of the reproducibility of good results in real world settings with intricate patterns due to its evasive nature and in-complete labels caused by the rarity of illicit transactions relative to the high volume of licit ones. Other recent research algorithmic development work in detecting money laundering have produced good accuracy predictions [13][15] [17]. Our research work seeks to do better. ...
Financial forensics has an important role in the field of finance to detect and investigate the occurrence of finance related crimes like money laundering. However, as with other forms of criminal activities, the forensics analysis of such activities is a complex undertaking with attempts by the adversaries to constantly upgrade their ability to evade detection. Also, the extent of the volume and complexity of financial activities or transactions further complicates the task of performing financial forensics. Machine Learning or Artificial Intelligence algorithms could be used to deal with such complexities. However, the challenge of limitedly available labeled datasets especially with fraudulent activities limits the means to develop efficient algorithms. Additionally, the complexity of defining precise search patterns of evasive fraudulent transactions further complicates this challenge. In this paper, we developed a novel deep set classifier algorithm based on meta learning and applied it to deal with the complexity deriving patterns of interest with sample of limitedly labelled transactions to detect fraudulent cryptocurrency money laundering transactions. We a unique approach to train our model with progressive provision of samples and the test result exceeds leading research algorithms.
With the growing popularity of cryptocurrencies, detecting potential market manipulation and fraudulent activities has become crucial for maintaining market integrity. In this study, we aim to detect anomalous Bitcoin transactions using an integrated approach by combining clustering techniques with statistical outlier detection. More specifically, anomalies were detected using three approaches: a distance-based method, flagging points with distances greater than the 95th percentile from their cluster centers; a statistical method, identifying transactions with any feature having an absolute Z-score greater than 3; and a hybrid approach, where transactions flagged by either method were considered anomalous. Using sample subset Bitcoin transaction data from 2015, our results showed that the combined approach was able to achieve the best performance with a total of 6492 (6.61%) detected anomalous transactions out of a total of 98,151 transactions.
Purpose
Money laundering has affected the economy in different ways, where the fraudulent activities are either domestic or abroad, resulting in financial instability globally. Anti-money laundering (AML) system is applied to detect and report any suspicious transactions. There are numerous approaches, techniques and algorithms in AML that are applied to fight against money laundering. This study aims to understand, identify and document the AML techniques applied to detect and prevent money laundering activities.
Design/methodology/approach
A systematic literature review is applied for searching articles based on methods used for AML from the electronic database platform. For review, data is considered from journal articles, books and conference proceedings with a time framework from 2014 to 2024.
Findings
In total, 53 papers were selected in the domain of money laundering concepts, issues and techniques of AML. The review articles are on the techniques of AML, such as machine learning, data mining, graph networks and artificial intelligence, which are applied to detect and prevent money laundering issues.
Originality/value
Money laundering, being a global issue, is a threat to the economy and society. Detecting money laundering activities is utmost required; this study contributes in selecting the articles that are involved in the application of techniques of AML in detecting and preventing money laundering activities. The results of this study can provide support instruments to identify the better AML techniques that are useful for practitioners and industry experts working in the AML domain. Further research can be explored with other AML techniques.
The Central Bank Digital Currencies (CBDCs) discourse includes various stakeholders from traditional and
nontraditional financial sectors. In this study, we analyze interviews conducted with four distinct groups of financial experts
shaping the global financial system: financial regulation experts (Regtech), global central bankers represented by the Basel
Committee for International Settlements (BIS), Federal Reserve representatives (FED) from the United States, and the
decentralized finance (DeFi) community. We explored a large volume of textual data, consisting of 20 interviews or panel
discussions from each group or 80 in total. The research question aims to identify the underlying connections and differences
in the CBDC adoption discourse among U.S. and global central banks, traditional financial market regulatory experts, and the
DeFi community. We conducted a mixed-methods study using factor analysis with WordStat software and content analysis
with NVivo software to map underlying topics and identify the opportunities and possible benefits or shortcomings of CBDC
adoption. Understanding the similarities and differences among different stakeholders' opinions can help policymakers and
central banks make more informed decisions.
Conference proceedings of the 3rd Blockchain and Cryptocurrency Conference (B2C' 2024), Tenerife (Canary Islands), Spain, 16-18 October 2024
The integration of machine learning (ML) algorithms in Anti-Money Laundering (AML) practices has garnered significant attention due to its potential to enhance the detection and prevention of illicit activities in the cryptocurrency ecosystem. This systematic literature review analysed the effectiveness of integrating ML algorithms in detecting and preventing crypto laundering activities, identify the most frequently used ML algorithms, examine trends in publication and research methodologies, and discuss key challenges and constraints associated with integrating ML technologies into AML frameworks. A comprehensive search strategy was employed to identify relevant studies, resulting in the inclusion of 52 articles published between 2019 and 2023. The findings reveal a growing interest in the field, with a notable increase in publications in recent years. Traditional ML models such as Logistic Regression, Random Forest, and Support Vector Machine (SVM) remain prevalent, while deep learning models like Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM) networks are gaining popularity. Graph Convolutional Networks (GCNs) have emerged as a significant area of exploration, particularly in the context of graph data analysis in cryptocurrencies. Despite advancements in ML, cryptocurrencies continue to pose a high risk of money laundering due to the practical challenge of implementation ownership of the various ML models. Future research should focus on how these challenges will be addressed to ensure the effective and sustainable use of ML technologies in real-world AML practices.
The influence of technology and developing information is indeed extraordinary on human life. Economic development is also inseparable from the growing technology, for example in transaction procedures in a matter. Bitcoin came up with a new innovation in the form of a cryptocurrency that uses a payment network from user to user. Crypto has become a phenomenon nowadays. Based on the results of the Global Web Index Survey, 10% of internet users in Indonesia already own digital currencies, it can be said that Indonesia is ranked 5th most crypto users in the world. Crypto or can be called crytocurrency has a fairly high risk. Then kirpto has a change in value that is only enthusiasm at any time. Krip toalso has a lack of regulation and still leaves legality issues. This research was conducted to determine the existence of bitcoin trading to the national economy. The use of bitcoin over time is increasing in Indonesia. For this reason, before the use of bitcoin is increasing, we must understand the influence and impact of bitcoin trading on the national economy. Only nine countries have legalized bitcoin, it is questionable why many countries have not legalized bitcoin. This study aims to find out how bitcoin trading conditions in Indonesia. The results of this journal will discuss the effect of bitcoin trading on the national economy even though in Indonesia it is prohibited and recognized as legal tender. This can be viewed from several factors such as from the nominal side of bitcoin which is considered excessive, especially in the picture of the economic crisis.
The heterogeneous and interoperable nature of the cyber-physical system (CPS) has enabled the smart grid (SG) to operate near the stability limits with an inconsiderable accuracy margin. This has imposed the need for more intelligent, predictive, fast, and accurate algorithms that are able to operate the grid autonomously to avoid cascading failures and/or blackouts. In this paper, a new comprehensive identification system is proposed that employs various machine learning architectures for classifying stability records in smart grid networks. Specifically, seven machine learning architectures are investigated, including optimizable support vector machine (SVM), decision trees classifier (DTC), logistic regression classifier (LRC), naïve Bayes classifier (NBC), linear discriminant classifier (LDC), k-nearest neighbor (kNN), and ensemble boosted classifier (EBC). The developed models are evaluated and contrasted in terms of various performance evaluation metrics such as accuracy, precision, recall, harmonic mean, prediction overhead, and others. Moreover, the system performance was evaluated on a recent and significant dataset for smart grid network stability (SGN_Stab2018), scoring a high identification accuracy (99.90%) with low identification overhead (4.17 μSec) for the optimizable SVM architecture. We also provide an in-depth description of our implementation in conjunction with an extensive experimental evaluation as well as a comparison with state-of-the-art models. The comparison outcomes obtained indicate that the optimized model provides a compact and efficient model that can successfully and accurately predict the voltage stability margin (VSM) considering different operating conditions, employing the fewest possible input features. Eventually, the results revealed the competency and superiority of the proposed optimized model over the other available models. The technique also speeds up the training process by reducing the number of simulations on a detailed power system model around operating points where correct predictions are made.
Classification and regression trees, as well as their variants, are off-the-shelf methods in Machine Learning. In this paper, we review recent contributions within the Continuous Optimization and the Mixed-Integer Linear Optimization paradigms to develop novel formulations in this research area. We compare those in terms of the nature of the decision variables and the constraints required, as well as the optimization algorithms proposed. We illustrate how these powerful formulations enhance the flexibility of tree models, being better suited to incorporate desirable properties such as cost-sensitivity, explainability, and fairness, and to deal with complex data, such as functional data.
Financial institutions must meet international regulations to ensure not to provide services to criminals and terrorists. They also need to continuously monitor financial transactions to detect suspicious activities. Businesses have many operations that monitor and validate their customer’s information against sources that either confirm their identities or disprove. Failing to detect unclean transaction(s) will result in harmful consequences on the financial institution responsible for that such as warnings or fines depending on the transaction severity level. The financial institutions use Anti-money laundering (AML) software sanctions screening and Watch-list filtering to monitor every transaction within the financial network to verify that none of the transactions can be used to do business with forbidden people. Lately, the financial industry and academia have agreed that machine learning (ML) may have a significant impact on monitoring money transaction tools to fight money laundering. Several research work and implementations have been done on Know Your Customer (KYC) systems, but there is no work on the watch-list filtering systems because of the compliance risk. Thus, we propose an innovative model to automate the process of checking blocked transactions in the watch-list filtering systems. To the best of our knowledge, this paper is the first research work on automating the watch-list filtering systems. We develop a Machine Learning - Component (ML-Component) that will be integrated with the current watch-list filtering systems. Our proposed ML-Component consists of three phases; monitoring, advising, and take action. Our model will handle a known critical issue, which is the false-positives (i.e., transactions that are blocked by a false alarm). Also, it will minimize the compliance officers’ effort, and provide faster processing time. We performed several experiments using different ML algorithms (SVM, DT, and NB) and found that the SVM outperforms other algorithms. Because our dataset is nonlinear, we used the polynomial kernel and achieved higher accuracy for predicting the transactionś decision, and the correlation matrix to show the relationship between the numeric features.
With the rapid expansion of intelligent resource-constrained devices and high-speed communication technologies, the Internet of Things (IoT) has earned wide recognition as the primary standard for low-power lossy networks (LLNs). Nevertheless, IoT infrastructures are vulnerable to cyber-attacks due to the constraints in computation, storage, and communication capacity of the endpoint devices. From one side, the majority of newly developed cyber-attacks are formed by slightly mutating formerly established cyber-attacks to produce a new attack that tends to be treated as normal traffic through the IoT network. From the other side, the influence of coupling the deep learning techniques with the cybersecurity field has become a recent inclination of many security applications due to their impressive performance. In this paper, we provide the comprehensive development of a new intelligent and autonomous deep-learning-based detection and classification system for cyber-attacks in IoT communication networks that leverage the power of convolutional neural networks, abbreviated as IoT-IDCS-CNN (IoT based Intrusion Detection and Classification System using Convolutional Neural Network). The proposed IoT-IDCS-CNN makes use of high-performance computing that employs the robust Compute Unified Device Architectures (CUDA) based Nvidia GPUs (Graphical Processing Units) and parallel processing that employs high-speed I9-core-based Intel CPUs. In particular, the proposed system is composed of three subsystems: a feature engineering subsystem, a feature learning subsystem, and a traffic classification subsystem. All subsystems were developed, verified, integrated, and validated in this research. To evaluate the developed system, we employed the Network Security Laboratory-Knowledge Discovery Databases (NSL-KDD) dataset, which includes all the key attacks in IoT computing. The simulation results demonstrated a greater than 99.3% and 98.2% cyber-attack classification accuracy for the binary-class classifier (normal vs. anomaly) and the multiclass classifier (five categories), respectively. The proposed system was validated using a K-fold cross-validation method and was evaluated using the confusion matrix parameters (i.e., true negative (TN), true positive (TP), false negative (FN), false positive (FP)), along with other classification performance metrics, including precision, recall, F1-score, and false alarm rate. The test and evaluation results of the IoT-IDCS-CNN system outperformed many recent machine-learning-based IDCS systems in the same area of study.
Abstract. Internet of Things (IoT) is a promising profound technology with tremendous expansion and effect. However, IoT infrastructures are vulnerable to cyber-attacks due to the constraints in computation, storage, and communication capacity for the endpoint devices such as thermostat, home appliance, etc. It was reported that 99% of the cyber-attacks are developed by slightly mutating previously known attacks to generate a new attack tending to be handled as a benign traffic through the IoT network. In this research, we developed a new intelligent self-reliant system that can detect mutations of IoT cyber-attacks using deep convolutional neural network (CNN) leveraging the power of CUDA based Nvidia-Quad GPUs for parallel computation and processing. Specifically, the proposed system is composed of three sub-systems: Feature Engineering subsystem, Feature Learning subsystem and Traffic classification subsystem. All subsystems are developed, verified, integrated, and validated in this research. To evaluate the developed system, we employed the NSL-KDD dataset which includes all the key attacks in the IoT computing. The simulation results showed a superior attacks’ classification accuracy over the state-of-art machine learning based intrusion detection systems employing similar dataset. The obtained results showed more than 99.3% and 98.2% of attacks’ classification accuracy for both binary-class classifier (normal vs anomaly) and multi-class classifier (five categories) respectively. All development steps and testing and verification results of the developed system are reported in the paper.
Purpose
The purpose of this paper is to develop, describe and validate a machine learning model for prioritising which financial transactions should be manually investigated for potential money laundering. The model is applied to a large data set from Norway’s largest bank, DNB.
Design/methodology/approach
A supervised machine learning model is trained by using three types of historic data: “normal” legal transactions; those flagged as suspicious by the bank’s internal alert system; and potential money laundering cases reported to the authorities. The model is trained to predict the probability that a new transaction should be reported, using information such as background information about the sender/receiver, their earlier behaviour and their transaction history.
Findings
The paper demonstrates that the common approach of not using non-reported alerts (i.e. transactions that are investigated but not reported) in the training of the model can lead to sub-optimal results. The same applies to the use of normal (un-investigated) transactions. Our developed method outperforms the bank’s current approach in terms of a fair measure of performance.
Originality/value
This research study is one of very few published anti-money laundering (AML) models for suspicious transactions that have been applied to a realistically sized data set. The paper also presents a new performance measure specifically tailored to compare the proposed method to the bank’s existing AML system.
The performance of neural networks with quadratic cost function (MSE cost function) are analyzed in terms of the adjustment rate of weights and its performance in multi-magnitude data processing using a qualitative mathematical method based on mean squared error. However, neural networks using quadratic cost functions exhibit low weight updating rates and variations in performances in multi-magnitude data processing. This study investigates the performance of neural networks using a quadratic relative error cost function (REMSE cost function). Two-node-to-one-node models are built to investigate the performance of the REMSE and MSE cost functions in adjustment rate of weights and multi-magnitude data processing. A three-layer neural network is employed to compare the training and prediction performances of the REMSE cost function and MSE cost function. Three LSTM networks are used to evaluate the differences between REMSE, MSE, and Logcosh in actual applications by learning stress and strain of soil. The results indicate that the REMSE cost function can notably accelerate the adjustment rate of weights and improve the performance of the neural network in small magnitude data regression. Applications of the REMSE cost function are also discussed.
Blockchain has numerous benefits such as decentralisation, persistency, anonymity and auditability. There is a wide spectrum of blockchain applications ranging from cryptocurrency, financial services, risk management, internet of things (IoT) to public and social services. Although a number of studies focus on using the blockchain technology in various application aspects, there is no comprehensive survey on the blockchain technology in both technological and application perspectives. To fill this gap, we conduct a comprehensive survey on the blockchain technology. In particular, this paper gives the blockchain taxonomy, introduces typical blockchain consensus algorithms, reviews blockchain applications and discusses technical challenges as well as recent advances in tackling the challenges. Moreover, this paper also points out the future directions in the blockchain technology.
The first crypto-currency appeared in 2009 when Bitcoin was born. Since then, numerous others have entered the market. The market for crypto-currencies has been incredibly volatile and, at its peak in 2017, one bitcoin was worth over $11,200, although it is now suffering from sustained losses in 2018.1, 2 These peaks and troughs have made crypto-currency value a popular media topic and hackers too have taken notice.
The market for crypto-currencies has been incredibly volatile and these peaks and troughs have made crypto-currency value a popular media topic. Hackers, too, have taken notice.
We have seen a recent sharp rise in crypto-jacking attacks, exploiting the power of victims' computers to mine crypto-currency. And alternative currencies also play a major role in ransomware attacks, being the payment method of choice. The chief defence, says Aaron Higbee of Cofense, is education. Phishing is a key element in these attacks and businesses need to help their employees to spot phishing attacks.
Money laundering has been affecting the global economy for many years. Large sums of money are laundered every year, posing a threat to the global economy and its security. Money laundering encompasses illegal activities that are used to make illegally acquired funds appear legal and legitimate. This paper aims to provide a comprehensive survey of machine learning algorithms and methods applied to detect suspicious transactions. In particular, solutions of anti-money laundering typologies, link analysis, behavioural modelling, risk scoring, anomaly detection, and geographic capability have been identified and analysed. Key steps of data preparation, data transformation, and data analytics techniques have been discussed; existing machine learning algorithms and methods described in the literature have been categorised, summarised, and compared. Finally, what techniques were lacking or under-addressed in the existing research has been elaborated with the purpose of pinpointing future research directions.
Proof of Work (PoW) powered blockchains currently account for more than 90% of the total market capitalization of existing digital cryptocurrencies. Although the security provisions of Bitcoin have been thoroughly analysed, the security guarantees of variant (forked) PoW blockchains (which were instantiated with different parameters) have not received much attention in the literature. This opens the question whether existing security analysis of Bitcoin's PoW applies to other implementations which have been instantiated with different consensus and/or network parameters.
In this paper, we introduce a novel quantitative framework to analyse the security and performance implications of various consensus and network parameters of PoW blockchains. Based on our framework, we devise optimal adversarial strategies for double-spending and selfish mining while taking into account real world constraints such as network propagation, different block sizes, block generation intervals, information propagation mechanism, and the impact of eclipse attacks. Our framework therefore allows us to capture existing PoW-based deployments as well as PoW blockchain variants that are instantiated with different parameters, and to objectively compare the tradeoffs between their performance and security provisions.
We perform a comprehensive measurement analysis of Silk Road, an anonymous, international online marketplace that operates as a Tor hidden service and uses Bitcoin as its exchange currency. We gather and analyze data over eight months between the end of 2011 and 2012, including daily crawls of the marketplace for nearly six months in 2012. We obtain a detailed picture of the type of goods sold on Silk Road, and of the revenues made both by sellers and Silk Road operators. Through examining over 24,400 separate items sold on the site, we show that Silk Road is overwhelmingly used as a market for controlled substances and narcotics, and that most items sold are available for less than three weeks. The majority of sellers disappears within roughly three months of their arrival, but a core of 112 sellers has been present throughout our measurement interval. We evaluate the total revenue made by all sellers, from public listings, to slightly over USD 1.2 million per month; this corresponds to about USD 92,000 per month in commissions for the Silk Road operators. We further show that the marketplace has been operating steadily, with daily sales and number of sellers overall increasing over our measurement interval. We discuss economic and policy implications of our analysis and results, including ethical considerations for future research in this area.
Spontaneous facial expression recognition under uncontrolled conditions is a hard task. It depends on multiple factors including shape, appearance and dynamics of the facial features, all of which are adversely affected by environmental noise and low intensity signals typical of such conditions. In this work, we present a novel approach to Facial Action Unit detection using a combination of Convolutional and Bi-directional Long Short-Term Memory Neural Networks (CNN-BLSTM), which jointly learns shape, appearance and dynamics in a deep learning manner. In addition, we introduce a novel way to encode shape features using binary image masks computed from the locations of facial landmarks. We show that the combination of dynamic CNN features and Bi-directional Long Short-Term Memory excels at modelling the temporal information. We thoroughly evaluate the contributions of each component in our system and show that it achieves state-of-the-art performance on the FERA-2015 Challenge dataset.
Anti-money laundering (AML) refers to a set of financial and technological controls that aim to combat the entrance of dirty money into financial systems. A robust AML system must be able to automatically detect any unusual/anomalous financial transactions committed by a customer. The paper presents a hybrid anomaly detection approach that employs clustering to establish customers’ normal behaviors and uses statistical techniques to determine deviation of a particular transaction from the corresponding group behavior. The approach implements a variant of Euclidean Adaptive Resonance Theory, termed as TEART, to group customers in different clusters. The paper also suggests an anomaly index, named AICAF, for ranking transactions as anomalous. The approach has been tested on a real data set comprising of 8.2 million transactions and the results suggest that TEART scales well in terms of the partitions obtained when compared to the traditional K-means algorithm. The presented approach marks transactions having high AICAF values as suspicious.
In this paper, we address the problem of detecting potentially illicit behavior in the context of Anti-Money Laundering (AML). We specifically address two requirements that arise when training machine learning models for AML: scalability and imbalance-resistance. By scalability we mean the ability to train the models to very large transaction datasets. By imbalance-resistance we mean the ability for the model to achieve suitable accuracy despite high class imbalance, i.e. the low number of instances of potentially illicit behavior relative to a large number of features that may characterize potentially illicit behavior. We propose a two-layered modelling concept. The first layer consists of a Logistic Regression model with simple features, which can be computed with low overhead. These features capture customer profiles as well as global aggregates of transaction histories. This layer filters out a proportion of customers whose activity patterns can be deemed non-illicit with high confidence. In the second layer, a gradient boosting model with complex features is used so as to classify the remaining customers. We anticipate that this two-layered approach achieves the stated requirements. Firstly, feature extraction is more scalable as the more computationally demanding features of the second layer do not need to be extracted for every customer. Secondly, the first layer acts as an undersampling method for the second layer, thus partially addressing the class imbalance. We validate the approach using a real dataset of customer profiles and transaction histories, together with labels provided by AML experts.
Ransomware is a rapidly growing threat to the data files of individuals and businesses. It encrypts files on an infected computer and holds the key to decrypt the files until the victim pays a ransom. This malware is responsible for hundreds of millions of dollars of losses annually. Due to the large amounts of money to be made, new versions appear frequently. This allows bypassing antivirus software and other intrusion detection methods. In this paper, we present a brief history of ransomware, the arguments for and against paying the ransom, best practices to prevent an infection, and to recover from an infection should one happen.
Money Laundering is the process of creating the appearance that large amounts of money obtained from serious crimes, such as drug trafficking or terrorist activity, originated from a legitimate source. Through money laundering, the launderer transforms the monetary proceeds derived from criminal activity into funds with an apparently legal source. The system that works against Money laundering is Anti-Money Laundering (AML) system. The existing system for Anti-Money Laundering accepts the bulk of data and converts it to large volumes reports that are tedious and topsy-turvy for a person to read without any help of software. To develop a structure to research in datamining, we create a taxonomy that combines research on patterns of observed fraud schemes with an appreciation of areas that benefit from a productive application of data mining. The aim of this study was to review research conducted in the field of fraud detection with an emphasis on detecting honey laundering and examine deficiencies based on data mining techniques. Which include a set of predefined rules and threshold values. In addition to this approach, data mining techniques are very convenient to detest money laundering patterns and detect unusual behavior. Therefore, unsupervised data mining technique will be more effective to detect new patterns of money laundering and can be crucial to enhance learning models based on classification methods. Of course, the development of new methods will be very useful to increase the accuracy of performance.
We provide a first systematic account of opportunities and limitations of anti-money laundering (AML) in Bitcoin, a decentralized cryptographic currency proliferating on the Internet. Our starting point is the observation that Bitcoin attracts criminal activity as many say it is an anonymous transaction system. While this claim does not stand up to scrutiny, several services offering increased transaction anonymization have emerged in the Bitcoin ecosystem - such as Bitcoin Fog, BitLaundry, and the Send Shared functionality of Blockchain.info. Some of these services routinely handle the equivalent of 6-digit dollar amounts. In a series of experiments, we use reverse-engineering methods to understand the mode of operation and try to trace anonymized transactions back to our probe accounts. While Bitcoin Fog and Blockchain.info successfully anonymize our test transactions, we can link the input and output transactions of BitLaundry. Against the backdrop of these findings, it appears unlikely that a Know-Your-Customer principle can be enforced in the Bitcoin system. Hence, we sketch alternative AML strategies accounting for imperfect knowledge of true identities but exploiting public information in the transaction graph, and discuss the implications for Bitcoin as a decentralized currency.
A purely peer-to-peer version of electronic cash would allow online payments to be sent directly from one party to another without going through a financial institution. Digital signatures provide part of the solution, but the main benefits are lost if a trusted third party is still required to prevent double-spending. We propose a solution to the double-spending problem using a peer-to-peer network. The network timestamps transactions by hashing them into an ongoing chain of hash-based proof-of-work, forming a record that cannot be changed without redoing the proof-of-work. The longest chain not only serves as proof of the sequence of events witnessed, but proof that it came from the largest pool of CPU power. As long as a majority of CPU power is controlled by nodes that are not cooperating to attack the network, they'll generate the longest chain and outpace attackers. The network itself requires minimal structure. Messages are broadcast on a best effort basis, and nodes can leave and rejoin the network at will, accepting the longest proof-of-work chain as proof of what happened while they were gone.
Money laundering (ML) is a serious crime which makes it necessary to develop detection methods in transactions. Some researches have been carried on, but the problem is not thoroughly solved. Aiming at the low detection rate of suspicious transaction at home and abroad in financial field, and with an analysis of radial basis function (RBF) neural network, we propose a radial basis function neural network model based on APC-III clustering algorithm and recursive least square algorithm for anti-money laundering (AML). APC-III clustering algorithm is used for determining the parameters of radial basis function in hidden layer, and recursive least square (RLS) algorithm is adopted to update weights of connections between hidden layer and output layer. The proposed method is compared against support vector machine (SVM) and outlier detection methods, which show that the proposed method has the highest detection rate and the lowest false positive rate. Thus our method is proved to have both theoretical and practical value for anti-money laundering.
Data Privacy Management, Cryptocurrencies and Blockchain Technology
- Tin Tironsakkul
Tironsakkul, Tin, et al. "Tracking mixed bitcoins." Data Privacy
Management, Cryptocurrencies and Blockchain Technology.
Springer, Cham, 2020. 447-457.
Man who hired hitman on Dark Web to kill exlover's boyfriend given 5 years' jail
- Shaffiq Alkhatib
Shaffiq Alkhatib. "Man who hired hitman on Dark Web to kill exlover's boyfriend given 5 years' jail", 18 Sept 2018. Available at:
https://www.straitstimes.com/singapore/courts-crime/man-whohired-hitman-on-dark-web-to-kill-ex-lovers-boyfriend-given-5-years (Accessed: 8 June 2021)
Money Laundering via Cryptocurrencies: All You Need to Know
- Tookitaki
Tookitaki.ai. " Money Laundering via Cryptocurrencies: All You
Need
to
Know",
8
June
2021.
Available
at:
https://www.tookitaki.ai/news-views/moneylaundering-viacryptocurrencies/ (Accessed: 8 June 2021)
Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics
- Mark Weber
Weber, Mark, et al. "Anti-money laundering in bitcoin:
Experimenting with graph convolutional networks for financial
forensics." arXiv preprint arXiv:1908.02591 (2019).
State of the Art Control of Atari Games Using Shallow Reinforcement Learning
- Y Liang
- M C Machado
- E Talvitie
- M Bowling
Y. Liang, M. C. Machado, E. Talvitie and M. Bowling, "State of the
Art Control of Atari Games Using Shallow Reinforcement
Learning", arXiv:1512.01563 [cs], Dec. 2015, [online] Available:
http://arxiv.org/abs/1512.01563.
Preprocessing Techniques for Neural Networks. Machine Learning, Github
- A Kalay
Kalay, A.: Preprocessing Techniques for Neural Networks. Machine
Learning,
Github.IO.
https://alfurka.github.io/2018-11-10-preprocessing-for-nn. (2018)
Multi-Class Classification of Firewall Log Files Using Shallow Neural Network for Network Security Applications
- Abdelraouf Qasem Abu Al-Haija
- Ishtaiwi
Qasem Abu Al-Haija, Abdelraouf Ishtaiwi, "Multi-Class
Classification of Firewall Log Files Using Shallow Neural Network
for Network Security Applications", Accepted, International
Conference on Soft Computing for Security Applications (ICSCS
2021), Springer -Advances in Intelligent Systems and Computing,
2021.
Bayesian Optimization with Gradients
- Jian Wu
- Matthias Poloczek
- Andrew Gordon Wilson
- Peter I Frazier
Jian Wu, Matthias Poloczek, Andrew Gordon Wilson, Peter I.
Frazier, "Bayesian Optimization with Gradients", arXiv:1703.04389,
2018.
Cross-Entropy Loss Function
- K E Koech
K.E. Koech, "Cross-Entropy Loss Function", Medium: towards data
science. (2020).
Understanding AUC -ROC Curve
- S Narkhede
S. Narkhede, "Understanding AUC -ROC Curve", Medium:
Towards Data Science, 2018.
Cross-Validation in Machine Learning. Medium: Towards data science
- P Gupta
Gupta, P. Cross-Validation in Machine Learning. Medium: Towards
data science. 2017. (accessed on 13 February 2020).