The recent wave of microarchitectural vulnerabilities in commodity hardware requires us to question our understanding of system security. We deplore that even for processor architectures and research prototypes with an explicit focus on security, open-source designs remain the exception. This article and call for action briefly surveys ongoing community efforts for developing a new generation of open security architectures, for which we collectively have a clear understanding of execution semantics and the resulting security implications. We advocate formal approaches to reason about the security guarantees that these architectures can provide, including the absence of microarchitectural bugs and side-channels. We consider such a principled approach essential in an age where society increasingly relies on interconnected and dependable control systems. Finally, we aim to inspire strong industrial and academic collaboration in such an engineering effort, which we believe is too monumental to be suitably addressed by a single enterprise or research community.
