Identifying Darknet Vendor Wallets by Matching Feedback Reviews with Bitcoin Transactions

Abstract

Darknet markets are e-commerce websites operating on the darknet and have grown rapidly in recent years. Darknet only allow cryptocurrencies as the payment methods, making it hard for law enforcement to trace those illicit transactions. In this paper, we present a method to identify vendors’ bitcoin addresses by matching vendors’ feedback reviews with bitcoin transactions in the public ledger. The problem is decomposed into two steps in formulation. In Step 1, we solve a bounding box matching between the set of feedback reviews and bitcoin transactions. In Step 2, we find the bitcoin addresses with a maximum coverage of the reviews. Baseline algorithm for Step 1 runs in quadratic time thus we develop a K-D tree to accelerate the computing. Problem in Step 2 is NP-hard thus we develop a greedy algorithm with an approximation ratio of (1 − 1/e) based on the submodular property of the objective function. We further propose a cost-effective algorithm to accelerate both steps effectively. Comprehensive experimental results have demonstrated the effectiveness and efficiency of the proposed method.