MétaCan
Menu
Back to cohort
Record W4415551573 · doi:10.70891/jair.2025.080018

Blockchain Fraud Detection Using Ensemble Graph Neural Networks

2025· article· W4415551573 on OpenAlexaff
Muhammad Zulqurnain Haider, Tayyaba Noreen, Mahwish Salman

Bibliographic record

VenueJournal of Artificial Intelligence Research · 2025
Typearticle
Language
FieldComputer Science
TopicImbalanced Data Classification Techniques
Canadian institutionsÉcole de Technologie SupérieureUniversité du Québec à Montréal
Fundersnot available
KeywordsGraphDatabase transactionAnonymityModular designCryptocurrencyBlockchainConvolutional neural networkArtificial neural network

Abstract

fetched live from OpenAlex

Cryptocurrencies like Bitcoin promise secure, decentralized transactions, but their anonymity also attracts illicit activity, posing a challenge to regulators and exchanges in maintaining control. This study tackles fraud detection in Bitcoin's transaction network using the Elliptic dataset, a real-world collection of labeled transactions. We combine three powerful graph neural networks Graph Convolutional Network (GCN), Graph Attention Network (GAT), and Graph Isomorphism Network (GIN) each capturing different patterns in the complex web of blockchain payments. By blending their predictions through ensemble techniques, such as tuned soft voting, we achieve a robust system that detects over 70% of illicit transactions while keeping false alarms below 1%. Our approach balances precision and coverage, making it practical for real-time anti-money laundering efforts. The modular framework adapts easily to new data, paving the way for scalable, reliable monitoring of cryptocurrency fraud.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.010
Threshold uncertainty score0.021

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.001
Science and technology studies0.0010.000
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.167
GPT teacher head0.432
Teacher spread0.264 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Artificial Intelligence ResearchSame topicImbalanced Data Classification TechniquesFrench-language works237,207