This study presents the correlational paraconsistent machine (CPM), a tool for anomaly detection that incorporates unsupervised models for traffic characterization and principles of paraconsistency, to inspect irregularities at the network traffic flow level. The CPM is applied for the mathematical foundation of uncertainties that may arise when establishing normal network traffic behavior profiles, providing means to support the consistency of the information sources chosen for anomaly detection. The experimental results from a real traffic trace evaluation suggest that CPM responses could improve anomaly detection rates. (C) 2017 Elsevier Inc. All rights reserved.
