Identifying Risky Vendors in Cryptocurrency P2P Marketplaces
Keywords: Online marketplace, Reputation system, Cryptocurrency, Financial fraud, Sybil attack, Online safety and trust
TL;DR: This paper highlights the possible shortcomings of existing reputation systems in online peer-to-peer cryptocurrency marketplaces, and proposes improvements to proactively identify and monitor risky vendors using publicly available signals.
Abstract: Peer-to-Peer (P2P) cryptocurrency exchanges are two-sided marketplaces, similar to eBay/Craigslist, where individuals can offer to sell cryptocurrency assets in exchange for payment.
Due to disintermediation, these marketplaces trade off increased privacy for higher risk (e.g., scams/fraud).
Although these marketplaces use feedback systems to encourage healthier transactions, anecdotal evidence suggests that feedback often fails to capture vendor-associated risks.
This work is the first to document the online safety of cryptocurrency P2P marketplaces, identify underlying issues in feedback-based reputation systems, and propose improved mechanisms for predicting and monitoring risky accounts.
We collect data from two cryptocurrency marketplaces, Paxful and LocalCoinSwap (LCS) for 12 months (06/2022--06/2023).
The data includes over 396\,000 listings, 67\,000 vendors, and 4.7 million historical feedback for Paxful; and about 52\,000 listings, 14\,000 users, and 146\,000 feedback for LCS.
First, our empirical data shows that the current feedback system does not sufficiently convey enough information about risky vendors, and is susceptible to reputation manipulation through user collusion and automation.
Second, combining various publicly available information, we build machine learning models to predict account suspension, and achieve a 0.86 F1-score and 0.93 AUC for Paxful.
Third, while our models appear to have limited transferability properties across markets, we identify which features most help account suspension across platforms.
Finally, we perform a month-long online evaluation and show that our models are significantly more successful than mere feedback-based reputation schemes at predicting which users will be suspended in the future.
Track: COI (submissions co-authored by SAC)
Submission Guidelines Scope: Yes
Submission Guidelines Blind: Yes
Submission Guidelines Format: Yes
Submission Guidelines Limit: Yes
Submission Guidelines Authorship: Yes
Student Author: Yes
Submission Number: 1007
Loading