An Abstraction-Refinement Approach to Verifying Convolutional Neural Networks

01/06/2022
by   Matan Ostrovsky, et al.
0

Convolutional neural networks have gained vast popularity due to their excellent performance in the fields of computer vision, image processing, and others. Unfortunately, it is now well known that convolutional networks often produce erroneous results - for example, minor perturbations of the inputs of these networks can result in severe classification errors. Numerous verification approaches have been proposed in recent years to prove the absence of such errors, but these are typically geared for fully connected networks and suffer from exacerbated scalability issues when applied to convolutional networks. To address this gap, we present here the Cnn-Abs framework, which is particularly aimed at the verification of convolutional networks. The core of Cnn-Abs is an abstraction-refinement technique, which simplifies the verification problem through the removal of convolutional connections in a way that soundly creates an over-approximation of the original problem; and which restores these connections if the resulting problem becomes too abstract. Cnn-Abs is designed to use existing verification engines as a backend, and our evaluation demonstrates that it can significantly boost the performance of a state-of-the-art DNN verification engine, reducing runtime by 15.7

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/02/2022

Abstraction and Refinement: Towards Scalable and Exact Verification of Neural Networks

As a new programming paradigm, deep neural networks (DNNs) have been inc...
research
06/24/2020

DeepAbstract: Neural Network Abstraction for Accelerating Verification

While abstraction is a classic tool of verification to scale it up, it i...
research
10/23/2022

Tighter Abstract Queries in Neural Network Verification

Neural networks have become critical components of reactive systems in v...
research
08/05/2022

Neural Network Verification using Residual Reasoning

With the increasing integration of neural networks as components in miss...
research
10/15/2020

Improving Neural Network Verification through Spurious Region Guided Refinement

We propose a spurious region guided refinement approach for robustness v...
research
07/20/2023

Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks

Abstraction is a key verification technique to improve scalability. Howe...
research
06/30/2020

Verification of indefinite-horizon POMDPs

The verification problem in MDPs asks whether, for any policy resolving ...

Please sign up or login with your details

Forgot password? Click here to reset