Sherlock - A tool for verification of neural network feedback systems

DOI10.1145/3302504.3313351OpenAlexW2937290319MaRDI QIDQ5239249

Susmit Jha, Sriram Sankaranarayanan, Souradeep Dutta, Xin Chen, Ashish Kumar Tiwari

Publication date: 22 October 2019

Published in: Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1145/3302504.3313351

zbMATH Keywords

neural networkpolynomial regressionhybrid systemreachability analysisflowpipe construction

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Specification and verification (program logics, model checking, etc.) (68Q60) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30)

Related Items (14)

An iterative scheme of safe reinforcement learning for nonlinear systems via barrier certificate generation ⋮ Sherlock ⋮ Static analysis of ReLU neural networks with tropical polyhedra ⋮ Synthesizing ReLU neural networks with two hidden layers as barrier certificates for hybrid systems ⋮ Reachability analysis of deep ReLU neural networks using facet-vertex incidence ⋮ Stability analysis of complementarity systems with neural network controllers ⋮ SOCKS: A Stochastic Optimal Control and Reachability Toolbox Using Kernel Methods ⋮ Strategy synthesis for partially-known switched stochastic systems ⋮ Learning lyapunov functions for hybrid systems ⋮ Quantitative Verification for Neural Networks using ProbStars ⋮ Verification of Recurrent Neural Networks with Star Reachability ⋮ BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic ⋮ Risk verification of stochastic systems with neural network controllers ⋮ Parameter synthesis of polynomial dynamical systems

Uses Software

• Flow*
• Reluplex

This page was built for publication: Sherlock - A tool for verification of neural network feedback systems