On the Spread of Viruses on the Internet

Abstract

We analyze the contact process on random graphs generated according to the preferential attachment scheme as a model for the spread of viruses in the Internet. We show that any virus with a positive rate of spread from a node to its neighbors has a non-vanishing chance of becoming epidemic. Quantitatively, we discover an interesting dichotomy: for it virus with effective spread rate λ, if the infection starts at a typical vertex, then it develops into an epidemic with probability λ^Θ ((log (1/ λ)/log log (1/ λ))), but on average the epidemic probability is λ^(Θ (1)).

Files

Additional details