Verisig 2.0: Verification of Neural Network Controllers Using Taylor Model Preconditioning
2021 ◽
pp. 249-262
Keyword(s):
AbstractThis paper presents Verisig 2.0, a verification tool for closed-loop systems with neural network (NN) controllers. We focus on NNs with tanh/sigmoid activations and develop a Taylor-model-based reachability algorithm through Taylor model preconditioning and shrink wrapping. Furthermore, we provide a parallelized implementation that allows Verisig 2.0 to efficiently handle larger NNs than existing tools can. We provide an extensive evaluation over 10 benchmarks and compare Verisig 2.0 against three state-of-the-art verification tools. We show that Verisig 2.0 is both more accurate and faster, achieving speed-ups of up to 21x and 268x against different tools, respectively.
2019 ◽
2020 ◽
Vol 34
(05)
◽
pp. 7626-7633
◽
Keyword(s):
2016 ◽
Vol 2016
(4)
◽
pp. 8-10
◽
Keyword(s):