Towards Improved Illicit Node Detection with Positive-Unlabelled Learning

We demonstrate the difference The nature of anonymity and decentralization of blockchain between the estimated values of evaluation metrics and the systems are making changes in the finance industry due actual values through an engineered PU dataset from the to its immutability, transparency, and automation [1]. Such Ethereum transaction dataset proposed in [15] to show the decentralized systems, however, are in the current stage of a concerns of assuming unlabeled data to be normal. We conduct temporarily unregulated environment [2], [3] with a variety of experiments to show that applying various PU classifiers can abnormal usages and security concerns. The abnormal usages help in improving the classification performance on two realworld include both the illicit activities clearly defined by traditional datasets with limited positive labels. The PU classifiers fiance: phishing scams, Ponzi schemes, money laundering, estimate potential identifiable class prior or treat the unlabeled etc. [4], and also the activities with no clear definition of examples as negative samples with label noise and learn with lawfulness or being just defined such as mixing services, i.e., biased models. We also compare various graph representation the mixer nodes involve in funds to confuse the trace of the methods for extracting node embedding vectors as the input transfers from the original source, e.g., US Department of the to get diverse data distribution for the same data to obtain Treasury declared Tornado Cash as a sanctioned entity [5], [6].