ADPP: A Novel Anomaly Detection and Privacy-Preserving Framework using Blockchain and Neural Networks in Tokenomics

Wei Yao, Jingyi Gu, Wenlu Du, Fadi P. Deek, Guiling Wang

Abstract: The increasing popularity of crypto assets has resulted in greater cryptocurrency investor interest andmore exposure in both industry and academia. Despite the substantial socioeconomic benefits, theanonymous character of cryptocurrency trading makes it prone to abuse and a magnet for illicit purposes,which cause monetary losses for individual traders and erosion in the standing of the tokenomics industry.To regulate the illicit behavior and secure users' privacy for cryptocurrency trading, we present anAnomaly Detection and Privacy-Preserving (ADPP) Framework integrating blockchain and deep learningtechnologies. Specifically, ADPP leverages blockchain technologies to build a user management platformthat ensures anonymity and enhances the privacy-preservation of user information. Atop the usermanagement system, an Anomaly Detection System adapts neural networks and imbalanced learning ontopological cryptocurrency flow among users to identify anomalous addresses and maintain a sanction listrepository. The experiments on the real-world dataset demonstrate the effectiveness and superiorperformance of ADPP. The flexible framework can be easily generalized to the crypto assets with publicreal-time transaction (e.g., Non-fungible Token), which takes up a significant proportion of marketcapitalization in the domain of tokenomics