An Accurate and Efficient Algorithm to Identify Malicious Nodes of a Graph.

The identification of misbehaving elements in a distributed system is an important task in many diverse settings that can be represented as graphs; this problem can be cast as the computation of a subset of the graph nodes by exploiting a pre-determined detection mechanism. In this paper we propose a simple yet accurate algorithm to compute the set of nodes of a graph suspected to be malicious that is based on the so called comparison detection model. In this framework, a node can play the role of the comparator for two of its neighbors and can provide a boolean result based on the actual status of both. The algorithm we propose has low computational complexity and linear space complexity; furthermore, it only requires one parameter to trade accuracy against computational cost. We also show it outperforms the state-of-the-art and performs equally very well on both synthetic and real world graphs.