POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
- 8 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (3) , 994-1007
Abstract
Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performance on challenging control problems. However, the potential adoption of NN controllers in real-life applications has been significantly impeded by the growing concerns over the safety of these NN-controlled systems (NNCSs). In this work, we present POLAR-Express, an efficient and precise formal reachability analysis tool for verifying the safety of NNCSs. POLAR-Express uses Taylor model (TM) arithmetic to propagate TMs layer-by-layer across an NN to compute an overapproximation of the NN. It can be applied to analyze any feedforward NNs with continuous activation functions, such as ReLU, Sigmoid, and Tanh activation functions that cover the common benchmarks for NNCS reachability analysis. Compared with its earlier prototype POLAR, we develop a novel approach in POLAR-Express to propagate TMs more efficiently and precisely across ReLU activation functions, and provide parallel computation support for TM propagation, thus significantly improving the efficiency and scalability. Across the comparison with six other state-of-the-art tools on a diverse set of common benchmarks, POLAR-Express achieves the best verification efficiency and tightness in the reachable set analysis. POLAR-Express is publicly available at https://github.com/ChaoHuang2018/POLAR_Tool .Keywords
All Related Versions
Funding Information
- National Science Foundation (CCF-1646497, CCF-1834324, CNS-1834701, CNS-1839511, IIS-1724341, CNS-2038853)
- Office of Naval Research (N00014-19-1-2496)
- U.S. Air Force Research Laboratory (FA8650-16-C-2642)
- International Science Partnerships Fund (ISPF) and the U.K. Research and Innovation through the EPSRC ECR International Collaboration Grants Program (EP/Y002644/1)
This publication has 58 references indexed in Scilit:
- POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems2022
- RINO: Robust INner and Outer Approximated Reachability of Neural Networks Controlled Systems2022
- Reachability Analysis for Cyber-Physical Systems: Are We There Yet?2022
- Verisig 2.0: Verification of Neural Network Controllers Using Taylor Model Preconditioning2021
- ReachNN*: A Tool for Reachability Analysis of Neural-Network Controlled Systems2020
- NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems2020
- A Linear Programming Relaxation Based Approach for Generating Barrier Certificates of Hybrid Systems2016
- Differential Equations and Dynamical Systems2001
- Applied Interval Analysis2001
- Lectures on Polytopes1995