DeepAI AI Chat
Log In Sign Up

ReachNN: Reachability Analysis of Neural-Network Controlled Systems

by   Chao Huang, et al.
Boston University
University of Dayton
Northwestern University

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.


page 2

page 3

page 4

page 6

page 7

page 8

page 9

page 11


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...

Reachability analysis of neural networks using mixed monotonicity

This paper presents a new reachability analysis tool to compute an inter...

Verifying Neural Networks Against Backdoor Attacks

Neural networks have achieved state-of-the-art performance in solving ma...

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

Over-approximating the reachable sets of dynamical systems is a fundamen...

Rational Neural Network Controllers

Neural networks have shown great success in many machine learning relate...

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

Neural networks (NNs) playing the role of controllers have demonstrated ...

Reachability Analysis of Neural Network Control Systems

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