Verifying Recurrent Neural Networks using Invariant Inference

04/06/2020
by   Yuval Jacoby, et al.
5

Deep neural networks are revolutionizing the way complex systems are developed. However, these automatically-generated networks are opaque to humans, making it difficult to reason about them and guarantee their correctness. Here, we propose a novel approach for verifying properties of a widespread variant of neural networks, called recurrent neural networks. Recurrent neural networks play a key role in, e.g., natural language processing, and their verification is crucial for guaranteeing the reliability of many critical systems. Our approach is based on the inference of invariants, which allow us to reduce the complex problem of verifying recurrent networks into simpler, non-recurrent problems. Experiments with a proof-of-concept implementation of our approach demonstrate that it performs orders-of-magnitude better than the state of the art.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

05/01/2017

From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing

In recent studies [1][13][12] Recurrent Neural Networks were used for ge...
11/14/2018

Verification of Recurrent Neural Networks Through Rule Extraction

The verification problem for neural networks is verifying whether a neur...
03/16/2018

Reviving and Improving Recurrent Back-Propagation

In this paper, we revisit the recurrent back-propagation (RBP) algorithm...
12/02/2018

Verifying Fairness Properties via Concentration

As machine learning systems are increasingly used to make real world leg...
05/11/2021

Recurrent Neural Networks to automate Quality assessment of Software Requirements

Many problems related to the quality of requirements arise during elicit...
09/22/2020

Property-Directed Verification of Recurrent Neural Networks

This paper presents a property-directed approach to verifying recurrent ...
06/05/2019

Complex Evolution Recurrent Neural Networks (ceRNNs)

Unitary Evolution Recurrent Neural Networks (uRNNs) have three attractiv...

Code Repositories

RnnVerify

Tool for formal verification of Recurrent Neural Networks


view repo
This week in AI

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