Hide and Seek: Outwitting Community Detection Algorithms

Community affiliation of a node plays an important role in determining its contextual position in the network, which may raise privacy concerns when a sensitive node wants to hide its identity in a network. Oftentimes, a target community seeks to protect itself from adversaries so that its constituent members remain hidden inside the network. The current study focuses on hiding such sensitive communities so that the community affiliation of the targeted nodes can be concealed. This leads to the problem of community deception, which investigates the avenues of minimally rewiring nodes in a network so that a given target community maximally hides from a community detection algorithm (CDA). We formalize the problem of community deception and introduce Network deception using permanence loss (NEURAL), a novel method that greedily optimizes a node-centric objective function to determine the rewiring strategy. Theoretical settings pose a restriction on the number of strategies that can be employed to optimize the objective function, which in turn reduces the overhead of choosing the best strategy from multiple options. We also show that our objective function is submodular and monotone. When tested on both synthetic and seven real-world networks, NEURAL is able to deceive six widely used CDAs. We benchmark its performance with respect to four state-of-the-art methods on four evaluation metrics. In addition, our qualitative analysis on three other attributed real-world networks reveals that NEURAL, quite strikingly, captures important metainformation about edges that otherwise could not be inferred by observing only their topological structures.