no code implementations • 16 Jul 2019 • He Zhu, Zikang Xiong, Stephen Magill, Suresh Jagannathan
Rather than enforcing safety by examining and altering the structure of a complex neural network implementation, our technique uses blackbox methods to synthesizes deterministic programs, simpler, more interpretable, approximations of the network that can nonetheless guarantee desired safety properties are preserved, even when the network is deployed in unanticipated or previously unobserved environments.