A Bayesian Model for Event-based Trust

Abstract

The application scenarios envisioned for ‘global ubiquitous computing’ have unique requirements that are often incompatible with traditional security paradigms. One alternative currently being investigated is to support security decision-making by explicit representation of principals' trusting relationships, i.e., via systems for computational trust. We focus here on systems where trust in a computational entity is interpreted as the expectation of certain future behaviour based on behavioural patterns of the past, and concern ourselves with the foundations of such probabilistic systems. In particular, we aim at establishing formal probabilistic models for computational trust and their fundamental properties. In the paper we define a mathematical measure for quantitatively comparing the effectiveness of probabilistic computational trust systems in various environments. Using it, we compare some of the systems from the computational trust literature; the comparison is derived formally, rather than obtained via experimental simulation as traditionally done. With this foundation in place, we formalise a general notion of information about past behaviour, based on event structures. This yields a flexible trust model where the probability of complex protocol outcomes can be assessed.