From cryptomarkets to the surface web: Scouting eBay for counterfeits

TL;DR

This paper presents an automated method to identify potential counterfeit products on eBay by leveraging data from cryptomarkets, using image and text similarity, and analyzing temporal changes to improve counterfeit detection.

Contribution

The study introduces a novel approach combining cryptomarket data with surface web analysis to detect counterfeits, demonstrating the potential for improved online marketplace monitoring.

Findings

Identified potential counterfeit products with increasing difficulty over time.

Product type and origin influence the similarity detection results.

Collected and analyzed 134,000 products over two periods for comprehensive insights.

Abstract

Detecting counterfeits on online marketplaces is challenging, and current methods struggle with the volume of sales on platforms like eBay, while cryptomarkets openly sell counterfeits. Leveraging information from 453 cryptomarket counterfeits, we automated a search for corresponding products on eBay, utilizing image and text similarity metrics. We collected data twice over 4-months to analyze changes with an average of 159 eBay products per cryptomarket item, totaling 134k products. We found identical products, which would warrant further investigation as to whether they are counterfeits. Results indicate increasing difficulty finding similar products over time, moderated by product type and origin. Future improved versions of the current system could be used to examine possible connections between cryptomarket and surface web listings more closely and could hold practical value in supporting the detection of counterfeits on the surface web.