Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications. (arXiv:2310.04381v1 [cs.CR])

In this paper, we present Hermes, an end-to-end framework to automatically
generate formal representations from natural language cellular specifications.
We first develop a neural constituency parser, NEUTREX, to process
transition-relevant texts and extract transition components (i.e., states,
conditions, and actions). We also design a domain-specific language to
translate these transition components to logical formulas by leveraging
dependency parse trees. Finally, we compile these logical formulas to generate
transitions and create the formal model as finite state machines. To
demonstrate the …

actions analysis cellular components conditions end end-to-end extract finite state framework language machines natural natural language network process protocols relevant security security analysis state states texts transition