Automatic Inference of High-Level Network Intents by Mining Forwarding Patterns

Abstract: There is a semantic gap between the high-level intents of network operators and the low-level configurations that achieve the intents. Previous works tried to bridge the gap using verification or synthesis techniques, both requiring formal specifications of the intended behavior which are rarely available or even known in the real world. This paper discusses an alternative approach for bridging the gap, namely to infer the high-level intents from the low-level network behavior. Specifically, we provide Anime, a framework and a tool that given a set of observed forwarding behavior, automatically infers a set of possible intents that best describe all observations. Our results show that Anime can infer high-quality intents from the low-level forwarding behavior with acceptable performance.