This paper studies the novel problem of influence-based com- munity deception. Tackling this problem amounts to devising tools to protect the users of a community from being discovered by community detection algorithms. The novel setting considers networks that have both edge directions and models the influence of nodes as edge weights. We present a deception strategy based on modularity. We conducted an experimental evaluation that shows the feasibility of our proposal
Influence-based Community Deception / Madi, SAIF ALDEEN ABDALLAH MOHAMMAD ALI; Pirro', Giuseppe. - (2022). (Intervento presentato al convegno The 11th International Conference on Complex Networks and their Applications tenutosi a Palermo).
Influence-based Community Deception
Saif Aldeen Madi;Giuseppe Pirro'
2022
Abstract
This paper studies the novel problem of influence-based com- munity deception. Tackling this problem amounts to devising tools to protect the users of a community from being discovered by community detection algorithms. The novel setting considers networks that have both edge directions and models the influence of nodes as edge weights. We present a deception strategy based on modularity. We conducted an experimental evaluation that shows the feasibility of our proposalI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.