Reachability In Simple Neural Networks

by   Marco Sälzer, et al.

We investigate the complexity of the reachability problem for (deep) neural networks: does it compute valid output given some valid input? It was recently claimed that the problem is NP-complete for general neural networks and specifications over the input/output dimension given by conjunctions of linear inequalities. We recapitulate the proof and repair some flaws in the original upper and lower bound proofs. Motivated by the general result, we show that NP-hardness already holds for restricted classes of simple specifications and neural networks. Allowing for a single hidden layer and an output dimension of one as well as neural networks with just one negative, zero and one positive weight or bias is sufficient to ensure NP-hardness. Additionally, we give a thorough discussion and outlook of possible extensions for this direction of research on neural network verification.


page 1

page 2

page 3

page 4


Reachability Is NP-Complete Even for the Simplest Neural Networks

We investigate the complexity of the reachability problem for (deep) neu...

Improved Ackermannian lower bound for the VASS reachability problem

This draft is a follow-up of the Ackermannian lower bound for the reacha...

Complexity of Reachability Problems in Neural Networks

In this paper we investigate formal verification problems for Neural Net...

Lower Bounds for the Reachability Problem in Fixed Dimensional VASSes

We study the complexity of the reachability problem for Vector Addition ...

First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)

This paper presents a summary and meta-analysis of the first three itera...

Verification of Binarized Neural Networks via Inter-Neuron Factoring

We study the problem of formal verification of Binarized Neural Networks...

Algorithms for Verifying Deep Neural Networks

Deep neural networks are widely used for nonlinear function approximatio...

Please sign up or login with your details

Forgot password? Click here to reset