Skip to Main Content
The emerging publish/subscribe communication paradigm for building large-scale distributed event notification systems, has been shown to exhibit excellent performance and scalability characteristics. Moreover, some work also focus on providing reliability and availability guarantees in the face of node crash and link failures. Such publish/subscribe systems are commonly used in cloud computing infrastructures. However, addressing the dependability concern due to malicious attacks or unintentional software errors, which can potentially corrupt the system, has largely been left untouched by researchers. In this paper, we first identify some of the potential problem areas related to Byzantine behavior in the publish/subscribe paradigm. Secondly, we propose several directions of research for designing a Byzantine fault-tolerant publish/subscribe system suitable for use as a cloud computing infrastructure.