POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems

03/31/2023
by   Yixuan Wang, et al.
0

Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performances on challenging control problems. However, the potential adoption of NN controllers in real-life applications also gives rise to a growing concern over the safety of these neural-network controlled systems (NNCSs), especially when used in safety-critical applications. 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 arithmetic to propagate Taylor models (TMs) across a neural network layer-by-layer to compute an overapproximation of the neural-network function. It can be applied to analyze any feed-forward neural network with continuous activation functions. We also present a novel approach to propagate TMs more efficiently and precisely across ReLU activation functions. In addition, POLAR-Express provides parallel computation support for the layer-by-layer propagation of TMs, thus significantly improving the efficiency and scalability over its earlier prototype POLAR. Across the comparison with six other state-of-the-art tools on a diverse set of benchmarks, POLAR-Express achieves the best verification efficiency and tightness in the reachable set analysis.

READ FULL TEXT

page 1

page 5

page 11

research
06/25/2021

POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems

We propose POLAR, a polynomial arithmetic framework that leverages polyn...
research
12/21/2017

Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations

Neural networks have been widely used to solve complex real-world proble...
research
06/25/2019

ReachNN: Reachability Analysis of Neural-Network Controlled Systems

Applying neural networks as controllers in dynamical systems has shown g...
research
03/02/2020

Reachability Analysis for Feed-Forward Neural Networks using Face Lattices

Deep neural networks have been widely applied as an effective approach t...
research
07/06/2022

Open- and Closed-Loop Neural Network Verification using Polynomial Zonotopes

We present a novel approach to efficiently compute tight non-convex encl...
research
11/23/2020

Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems with Deep Neural Network Components

We present a method for computing exact reachable sets for deep neural n...
research
04/11/2023

Exact and Cost-Effective Automated Transformation of Neural Network Controllers to Decision Tree Controllers

Over the past decade, neural network (NN)-based controllers have demonst...

Please sign up or login with your details

Forgot password? Click here to reset