Quantifying information leakage in process calculi

Building on simple information-theoretic concepts, we study two quantitative models of information leakage in the pi-calculus. The first model presupposes an attacker with an essentially unlimited computational power. The resulting notion of absolute leakage, measured in bits, is in agreement with secrecy as defined by Abadi and Gordon: a process has an absolute leakage of zero precisely when it satisfies secrecy. The second model assumes a restricted observation scenario, inspired by the testing equivalence framework, where the attacker can only conduct repeated success-or-failure experiments on processes. Moreover, each experiment has a cost in terms of communication effort. The resulting notion of leakage rate, measured in bits per action, is in agreement with the first model: the maximum amount of information that can be extracted by repeated experiments coincides with the absolute leakage A of the process. Moreover, the overall extraction cost is at least A/R, where R is the rate of the process. The compositionality properties of the two models are also investigated.