Who Audits the Auditor? Tamper-Proof Fraud Detection with Blockchain-Anchored Explainable ML

arXiv cs.LG / 4/27/2026

💬 OpinionDeveloper Stack & InfrastructureIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that enterprise fraud detection failures often stem from compromised audit trails—insiders can tamper with logs or bypass approvals—creating a fundamental “trust gap” about who audits the auditor.
It proposes a tamper-evident fraud detection system that uses smart contracts to atomically anchor both ML predictions and workflow execution to an immutable blockchain ledger.
The approach records every transaction, prediction, and explanation in a way that cannot be retroactively altered, enabling cryptographically verifiable decision trails for regulatory auditability.
Reported results show competitive detection performance (F1 = 0.895, PR-AUC = 0.974) along with low operational overhead, including sub-25 ms inference latency and low Layer-2 transaction costs (under $0.01, validated via PolygonScan).
The system is positioned for enterprise-scale use, supporting workloads of 10,000+ monthly payments with economically viable deployment on Layer-2 networks.

Abstract

In enterprise fraud detection, model accuracy alone is insufficient when insiders can tamper with audit logs or bypass approval workflows. Real-world incidents show that fraud often persists not because detection algorithms fail, but because the audit trail itself is controllable by privileged operators. This exposes a fundamental trust gap: *who audits the auditor?* We present a tamper-evident fraud detection system that anchors both ML predictions and workflow execution to an immutable blockchain ledger. Rather than using blockchain as passive storage, we enforce the entire approval process through smart contracts, ensuring that every transaction, prediction, and explanation is atomically recorded and cannot be retroactively modified. Our detection module achieves competitive accuracy (F1 = 0.895, PR-AUC = 0.974) while providing cryptographically verifiable decision trails that support regulatory auditability requirements (e.g., GDPR Article 22). System evaluation shows sub-25 ms inference latency and economically viable deployment on Layer-2 networks at under \$0.01 per transaction (validated against PolygonScan data), supporting enterprise-scale workloads of 10,000+ monthly payments.