Search for: All records

Notions of transition invariants and closure certificates have seen recent use in the formal verification of controlled dy- namical systems against ω-regular properties. The existing approaches face limitations in two directions. First, they re- quire a closed-form mathematical expression representing the model of the system. Such an expression may be difficult to find, too complex to be of any use, or unavailable due to security or privacy constraints. Second, finding such invari- ants typically rely on optimization techniques such as sum-of- squares (SOS) or satisfiability modulo theory (SMT) solvers. This restricts the classes of systems that need to be formally verified. To address these drawbacks, we introduce a notion of neural closure certificates. We present a data-driven algo- rithm that trains a neural network to represent a closure cer- tificate. Our approach is formally correct under some mild as- sumptions, i.e., one is able to formally show that the unknown system satisfies the ω-regular property of interest if a neural closure certificate can be computed. Finally, we demonstrate the efficacy of our approach with relevant case studies.