The requirement for spontaneous interaction in ubiquitous computing creates security issues over and above those present in other areas of computing, deeming traditional approaches ineffective. As a result, to support secure collaborations entities must implement selfprotective measures. Trust management is a solution well suited to this task as reasoning about future interactions is based on the outcome of past ones. This requires monitoring of interactions as they take place. Such monitoring also allows us to take corrective action when interactions are proceeding unsatisfactorily. In this vein, we first present a trust-based model of interaction based on event structures. We then describe our ongoing work in the development of a monitor architecture which enables self-protective actions to be carried out at critical points during principal interaction. Finally, we discuss some potential directions for future work.