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

06/25/2021
by   Chao Huang, et al.
0

We propose POLAR, a polynomial arithmetic framework that leverages polynomial overapproximations with interval remainders for bounded-time reachability analysis of neural network-controlled systems (NNCSs). Compared with existing arithmetic approaches that use standard Taylor models, our framework uses a novel approach to iteratively overapproximate the neuron output ranges layer-by-layer with a combination of Bernstein polynomial interpolation for continuous activation functions and Taylor model arithmetic for the other operations. This approach can overcome the main drawback in the standard Taylor model arithmetic, i.e. its inability to handle functions that cannot be well approximated by Taylor polynomials, and significantly improve the accuracy and efficiency of reachable states computation for NNCSs. To further tighten the overapproximation, our method keeps the Taylor model remainders symbolic under the linear mappings when estimating the output range of a neural network. We show that POLAR can be seamlessly integrated with existing Taylor model flowpipe construction techniques, and demonstrate that POLAR significantly outperforms the current state-of-the-art techniques on a suite of benchmarks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 11

04/16/2021

Arithmetic Distribution Neural Network for Background Subtraction

We propose a new Arithmetic Distribution Neural Network (ADNN) for learn...
06/25/2019

ReachNN: Reachability Analysis of Neural-Network Controlled Systems

Applying neural networks as controllers in dynamical systems has shown g...
11/15/2021

Reachability analysis of neural networks using mixed monotonicity

This paper presents a new reachability analysis tool to compute an inter...
12/14/2016

Reverse Engineering of Irreducible Polynomials in GF(2^m) Arithmetic

Current techniques for formally verifying circuits implemented in Galois...
06/14/2021

Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network

Fully homomorphic encryption (FHE) is one of the prospective tools for p...
12/09/2021

The Fundamental Limits of Interval Arithmetic for Neural Networks

Interval analysis (or interval bound propagation, IBP) is a popular tech...
05/28/2019

NIL: Learning Nonlinear Interpolants

Nonlinear interpolants have been shown useful for the verification of pr...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.