ReachNN: Reachability Analysis of Neural-Network Controlled Systems

06/25/2019
by   Chao Huang, et al.
0

Applying neural networks as controllers in dynamical systems has shown great promises. However, it is critical yet challenging to verify the safety of such control systems with neural-network controllers in the loop. Previous methods for verifying neural network controlled systems are limited to a few specific activation functions. In this work, we propose a new reachability analysis approach based on Bernstein polynomials that can verify neural-network controlled systems with a more general form of activation functions, i.e., as long as they ensure that the neural networks are Lipschitz continuous. Specifically, we consider abstracting feedforward neural networks with Bernstein polynomials for a small subset of inputs. To quantify the error introduced by abstraction, we provide both theoretical error bound estimation based on the theory of Bernstein polynomials and more practical sampling based error bound estimation, following a tight Lipschitz constant estimation approach based on forward reachability analysis. Compared with previous methods, our approach addresses a much broader set of neural networks, including heterogeneous neural networks that contain multiple types of activation functions. Experiment results on a variety of benchmarks show the effectiveness of our approach.

READ FULL TEXT

page 2

page 3

page 4

page 6

page 7

page 8

page 9

page 11

research
03/07/2023

A Neurosymbolic Approach to the Verification of Temporal Logic Properties of Learning enabled Control Systems

Signal Temporal Logic (STL) has become a popular tool for expressing for...
research
11/15/2021

Reachability analysis of neural networks using mixed monotonicity

This paper presents a new reachability analysis tool to compute an inter...
research
05/14/2022

Verifying Neural Networks Against Backdoor Attacks

Neural networks have achieved state-of-the-art performance in solving ma...
research
12/14/2022

Automated Reachability Analysis of Neural Network-Controlled Systems via Adaptive Polytopes

Over-approximating the reachable sets of dynamical systems is a fundamen...
research
07/12/2023

Rational Neural Network Controllers

Neural networks have shown great success in many machine learning relate...
research
03/31/2023

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

Neural networks (NNs) playing the role of controllers have demonstrated ...
research
01/28/2023

Reachability Analysis of Neural Network Control Systems

Neural network controllers (NNCs) have shown great promise in autonomous...

Please sign up or login with your details

Forgot password? Click here to reset