Contact Evidence-driven Blackhole Detection based on machine learning (CEBD) is proposed to improve the routing performance in the OppNet, where the blackhole behaviors may occur. The paper has been published in TCSS.
We investigate the evidence construction, i.e., the direct and indirect evidence with the statistical parameters in message exchange. Specifically, we construct behavior classifiers to distinguish the blackhole behaviors from rational ones and design the collusion filtering strategy to improve the detection accuracy by separating corrupted nodes from rational ones, respectively, laying a behavior identification foundation.
Based on the classifying results, the 'detecting' nodes will not cooperate with the 'detected' nodes (i.e., the 'Positive' node in the Blackhole detection).