How Reliable Is the Multi-Input Heuristic for Bitcoin Address Clustering in Law Enforcement Contexts?

2026-07-08

AI Summary

This study addresses the widespread yet insufficiently validated use of the multi-input heuristic (MIH) in Bitcoin address clustering by law enforcement. Leveraging legally mandated, ground-truth address-to-entity mappings reported by European crypto-asset service providers, the authors construct a reproducible evaluation framework and conduct a fine-grained, multi-level empirical analysis of MIH using nine standard clustering metrics. Their findings reveal that MIH achieves only 0.36 precision and 0.44 recall at the full-cluster level and fails to effectively recover addresses for certain entity types. These results demonstrate that MIH’s reliability is highly contingent on both the evaluation dimension and the specific entity category, thereby challenging the prevailing assumption of its default validity in forensic practice.

Abstract

Address clustering is an important technique in blockchain forensics, widely employed by law enforcement to trace illicit crypto asset flows. The multi-input heuristic (MIH), which clusters addresses potentially associated with the same entity, is the most widely used. Yet, despite its broad adoption, the MIH has rarely been evaluated against reliable ground truth data. We implement a reusable evaluation framework covering nine established metrics and apply it to ground truth address-to-entity mappings obtained directly from European crypto asset service providers under legally mandated reporting obligations. When evaluation is restricted to reported addresses, the MIH appears strong at dataset level: we observe no mergers between reported services and recover same-service address pairs with recall $0.71$. However, this result is driven by one large service and ignores unlabeled addresses absorbed into full clusters. Metrics that assess the full clusters show substantially lower precision and recall ($0.36$ and $0.44$), meaning that services are often only partially recovered or embedded in larger clusters. Entity-level results further reveal near-complete failures for some services. When MIH-based clusters are used to support criminal suspicion, preliminary seizure of crypto assets to secure later forfeiture/ confiscation, or as evidence in trial proceedings, prosecutors and judges must account for the heuristic's metric-dependent and entity-dependent reliability.

Problem

• Bitcoin address clustering
• multi-input heuristic
• blockchain forensics
• law enforcement
• ground truth evaluation

Innovation

• multi-input heuristic
• blockchain forensics
• address clustering
• ground truth evaluation
• crypto asset tracing