Detecting Illicit Entities in Bitcoin using Supervised Learning of Ensemble Decision Trees

Abstract

Since its inception in 2009, Bitcoin has been mired in controversies for providing a haven for illegal activities. Several types of illicit users hide behind the blanket of anonymity. Uncovering these entities is key for forensic investigations. Current methods utilize machine learning for identifying these illicit entities. However, the existing approaches only focus on a limited category of illicit users. The current paper proposes to address the issue by implementing an ensemble of decision trees for supervised learning. More parameters allow the ensemble model to learn discriminating features that can categorize multiple groups of illicit users from licit users. To evaluate the model, a dataset of 2059 real-life entities on Bitcoin was extracted from the Blockchain. Nine features were engineered to train the model for segregating 28 different licit-illicit categories of users. The proposed model provided a reliable tool for forensic study. Empirical evaluation of the proposed model vis-a-vis three existing benchmark models was performed to highlight its efficacy. Experiments showed that the specificity and sensitivity of the proposed model were comparable to other models.

A comprehensive review of significant learning for anomalous transaction detection using a machine learning method in a decentralized blockchain network

“…2020 [96] Journal XGBoost Ethereum illegal activity XGBoost classification mode swiftly and successfully detects illicit behaviour on the Ethereum network. 2020 [97] Journal Ensemble DT Bitcoin illicit entities According to the study's findings, 66 percent of users were correctly classified using the proposed model 2020 [98] Journal Multi-layer Perceptron (MLP) Bitcoin Scam We found 6,395 addresses explicitly offered by scam cases by actively hunting for them and using ML to identify the findings. 2021 [9] Journal T he results of the analysis show that RF has achieved the highest results compared to other models, that is, the value of F1 (95.9%).…”

Combining Multiple Classifiers using Ensemble Method for Anomaly Detection in Blockchain Networks: A Comprehensive Review

“…In earlier study, numerous ML algorithms have been applied in supervised [57] and unsupervised learning [58] for anomaly detection in blockchain networks. Random Forest (RF) [59], Decision Tree (DT) (j48) [60], Extreme Gradient Boosting (XGBoost) [61], Adaptive Boosting (AdaBoost) [62], secureSVM [63], Light Gradient Boosted Machine (LightGBM) [64], K-Nearest Neighbour (KNN) [65], Support Vector Machines (SVM) [66], Naïve Bayes (NB) [67] and Isolation Forest (IF) [68] are examples of supervised learning models. Among the models in unsupervised learning that have been utilized are One Class Support Vector Machine (OCSVM) [69], K-means [70], Density Based Spatial Clustering of Application with Noise (DBSCAN) [71] and Long Short Term Memory (LSTM) [72].…”

Anomaly detection in blockchain using network representation and machine learning

“…Identification of abnormal activities within Bitcoin transactions has been intensively addressed in the past. Such works addressed a broad range of security issues and challenges, including, but not limited to, privacy and deanonymization investigation, 4 botnets detection, 5 abnormal and fraudulent transactions detection, 6,7 malicious users and miners detection, [8][9][10][11] darknet markets, 12 money laundering and drug trading, 13 etc. However, it is worth noting that feature engineering (ie, which comprises various mechanisms and approaches including network embeddings, clustering, and network traffic characterization) is a vital and crucial aspect of most of Bitcoin-based research works that mainly focus on illegitimate user and miner activity identification.…”

“…This work falls within the scope of fraud detection in all types of financial transaction systems, where a considerable volume of literature exists such as. 2,7,11,[23][24][25] It is substantial to note that such a research problem might be generalized over those in other network settings that could or could not comprise financial transactions. Therefore, we aim at exploring and evaluating the more general issue of anomaly identification within Bitcoin transactions network.…”