Towards Repairing Neural Networks Correctly

12/03/2020
by   Guoliang Dong, et al.
0

Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication). While many impressive static verification techniques have been proposed to tackle the correctness problem of neural networks, it is possible that static verification may never be sufficiently scalable to handle real-world neural networks. In this work, we propose a runtime verification method to ensure the correctness of neural networks. Given a neural network and a desirable safety property, we adopt state-of-the-art static verification techniques to identify strategically locations to introduce additional gates which "correct" neural network behaviors at runtime. Experiment results show that our approach effectively generates neural networks which are guaranteed to satisfy the properties, whilst being consistent with the original neural network most of the time.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

07/22/2020

SOCRATES: Towards a Unified Platform for Neural Network Verification

Studies show that neural networks, not unlike traditional programs, are ...
04/26/2021

Fast Falsification of Neural Networks using Property Directed Testing

Neural networks are now extensively used in perception, prediction and c...
10/31/2019

An Abstraction-Based Framework for Neural Network Verification

Deep neural networks are increasingly being used as controllers for safe...
05/14/2022

Verifying Neural Networks Against Backdoor Attacks

Neural networks have achieved state-of-the-art performance in solving ma...
02/19/2019

Fast Neural Network Verification via Shadow Prices

To use neural networks in safety-critical settings it is paramount to pr...
04/20/2022

Causality-based Neural Network Repair

Neural networks have had discernible achievements in a wide range of app...
06/24/2021

Online Verification of Deep Neural Networks under Domain or Weight Shift

Although neural networks are widely used, it remains challenging to form...
This week in AI

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