Towards Improved Illicit Node Detection with Positive-Unlabelled Learning

Junliang Luo, Farimah Poursafaei, Xue Liu
3/4/2023
cs.LG

No official code found. Best implementation: JunLLuo/Illicit-transaction-address-detect-PU-Learning (2 stars, last commit 2025-05-05).

Abstract

Detecting illicit nodes on blockchain networks is a valuable task for strengthening future regulation. Recent machine learning-based methods proposed to tackle the tasks are using some blockchain transaction datasets with a small portion of samples labeled positive and the rest unlabelled (PU). Albeit the assumption that a random sample of unlabeled nodes are normal nodes is used in some works, we discuss that the label mechanism assumption for the hidden positive labels and its effect on the evaluation metrics is worth considering. We further explore that PU classifiers dealing with potential hidden positive labels can have improved performance compared to regular machine learning models. We test the PU classifiers with a list of graph representation learning methods for obtaining different feature distributions for the same data to have more reliable results.

View on arXivView PDF

Code Implementations(1)

JunLLuo/Illicit-transaction-address-detect-PU-LearningCommunity100%

Implementation of the paper: Towards Improved Illicit Node Detection with Positive-Unlabelled Learning

20PythonJul 17, 20231 years ago
blockchaingraph-representation-learningmachine-learningpu-learning

Similar Papers

Effective Illicit Account Detection on Large Cryptocurrency MultiGraphs

80% match1 repo92023

Chainlet Orbits: Topological Address Embedding for the Bitcoin Blockchain

80% match2023

Identifying Money Laundering Subgraphs on the Blockchain

79% match1 repo102024

Detecting Anomalies in Blockchain Transactions using Machine Learning Classifiers and Explainability Analysis

79% match2024

Learning from sanctioned government suppliers: A machine learning and network science approach to detecting fraud and corruption in Mexico

79% match2025

Positive-Unlabeled Node Classification with Structure-aware Graph Learning

79% match2023

Cite this paper

@article{luo2023towards,
  title  = {Towards Improved Illicit Node Detection with Positive-Unlabelled Learning},
  author = {Junliang Luo and Farimah Poursafaei and Xue Liu},
  year   = {2023},
  eprint = {2303.02462},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.02462v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.02462.svg)](https://codeofpaper.com/paper/2303.02462)

Discussion