Explainable Profiling Attacks on Ethereum Blockchain Users Based on Volumetric and Temporal Behaviour

Abstract

One of many different application areas of the blockchain technology is crypto-currencies. Products like Bitcoin and Solana provide financial services that are unmediated, distributed and anonymous. Among various blockchains, Ethereum stands out due to its support of smart contracts. However, softly authenticated transactions occuring on such platforms facilitate crimes like money laundering and sales of illegal items/services. Denanonymization, over blockchains, refers to identifying distinct accounts of the same person and is used for tracking illegal trafficking of cryptocurrencies. In this study, our purpose is to increase the rate of success of deanonymization and to support explainable approaches. Towards this aim, we imitate blockchain analysts and propose 19 novel heuristic features that are volumetric and temporal. Empirical experiments indicate that temporal features increase the attack success rate by 39%. Shapley values adapted from the cooperative game theory field support this finding.