Self-Repairing Peer-to-Peer Networks

Abstract

In this paper we study the resilience of peer-to-peer networks to preferential attacks. We define a network model and experiment with three di erent simple repairing algorithms, out of which the so called 2nd neighbor rewiring algorithm is found to be e ective and plausible for keeping a large connected component in the network, in spite of the continuous attacks. While our motivation comes from peer-to-peer file sharing networks, we believe that our results are more general and applicable in a wide range of networks. All this work was done as a student project in the Complex Systems Summer School 2004, organized by the Santa Fe Institute in Santa Fe, NM, USA.