In this paper, we present a trust-modeling framework for message propagation and evaluation in vehicular ad hoc networks. In the framework, peers share information regarding road condition or safety, and others provide opinions about whether the information can be trusted. More specifically, our trust-based message propagation model collects and propagates peers' opinions in an efficient, secure, and scalable way by dynamically controlling information dissemination. The trust-based message evaluation model allows peers to derive a local action decision about whether to follow the information by evaluating the information in a distributed and collaborative fashion while taking into account others' opinions. Experimental results demonstrate that our proposed trust-modeling framework promotes network scalability and system effectiveness, which are the two essentially important factors for the popularization of vehicular ad hoc networks, in information propagation and evaluation under the pervasive presence of false information. In particular, we clarify how our relay control serves to decrease the number of inappropriate actions taken on the basis of malicious information and enables honest peers to produce a greater number of deliveries within the network.