Analyses of routing protocols security are nearly always supported by simulations, which often evaluate the ability to deliver messages to a given destination. Several competing definitions for secure routing exist, but to our knowledge , they only address source routing protocols. In this paper, we propose the notion of corruptibility, a quantitative computational definition for routing security based on the attacker's ability to alter the routes used by messages. We first define incorruptibility, and we follow with the definition of bounded corruptibil-ity, which uses two routing protocols as bounds for the evaluated protocol. These definitions are then illustrated with several routing algorithms.