EcoSta 2021: Start Registration
View Submission - EcoSta2021
A0689
Title: Topology-based anomaly detection in dynamic multilayer networks Authors:  Dorcas Ofori-Boateng - Portland State University (United States) [presenting]
Yulia Gel - University of Texas at Dallas (United States)
Ignacio Segovia-Dominguez - University of Texas at Dallas (United States)
Murat Kantarcioglu - UNIVERSITY OF TEXAS AT DALLAS (United States)
Cuneyt Akcora - University of Manitoba (Canada)
Abstract: Motivated by the recent surge of criminal activities involving cross-cryptocurrency trades, we introduce a new topological perspective to structural anomaly detection in dynamic multilayer networks. We postulate that anomalies in the underlying blockchain transaction graph that are composed of multiple layers are likely to be also manifested in anomalous patterns of the network shape properties. As such, we invoke the machinery of clique persistent homology on graphs to systematically and efficiently track the evolution of the network shape and, as a result, to detect changes in the underlying network topology and geometry. We develop a new persistence summary for multilayer networks, called the stacked persistence diagram, and prove its stability under input data perturbations. We validate our new topological anomaly detection framework in application to dynamic multilayer networks from the Ethereum Blockchain and the Ripple Credit Network and show that our stacked PD approach substantially outperforms the state-of-art techniques, yielding up to 40\% gains in precision.