Verifying And Interpreting Neural Networks using Finite Automata

by   Marco Sälzer, et al.
Universität Kassel

Verifying properties and interpreting the behaviour of deep neural networks (DNN) is an important task given their ubiquitous use in applications, including safety-critical ones, and their blackbox nature. We propose an automata-theoric approach to tackling problems arising in DNN analysis. We show that the input-output behaviour of a DNN can be captured precisely by a (special) weak Büchi automaton of exponential size. We show how these can be used to address common verification and interpretation tasks like adversarial robustness, minimum sufficient reasons etc. We report on a proof-of-concept implementation translating DNN to automata on finite words for better efficiency at the cost of losing precision in analysis.


page 1

page 2

page 3

page 4


Neural Network Verification with Proof Production

Deep neural networks (DNNs) are increasingly being employed in safety-cr...

Boosting the Robustness Verification of DNN by Identifying the Achilles's Heel

Deep Neural Network (DNN) is a widely used deep learning technique. How ...

Verifying Recurrent Neural Networks using Invariant Inference

Deep neural networks are revolutionizing the way complex systems are dev...

Refactoring Neural Networks for Verification

Deep neural networks (DNN) are growing in capability and applicability. ...

Performance Analysis of Out-of-Distribution Detection on Trained Neural Networks

Several areas have been improved with Deep Learning during the past year...

Verification of Size Invariance in DNN Activations using Concept Embeddings

The benefits of deep neural networks (DNNs) have become of interest for ...

Input/Output Stochastic Automata with Urgency: Confluence and weak determinism

In a previous work, we introduced an input/output variant of stochastic ...

Please sign up or login with your details

Forgot password? Click here to reset