Refactoring Neural Networks for Verification

by   David Shriver, et al.

Deep neural networks (DNN) are growing in capability and applicability. Their effectiveness has led to their use in safety critical and autonomous systems, yet there is a dearth of cost-effective methods available for reasoning about the behavior of a DNN. In this paper, we seek to expand the applicability and scalability of existing DNN verification techniques through DNN refactoring. A DNN refactoring defines (a) the transformation of the DNN's architecture, i.e., the number and size of its layers, and (b) the distillation of the learned relationships between the input features and function outputs of the original to train the transformed network. Unlike with traditional code refactoring, DNN refactoring does not guarantee functional equivalence of the two networks, but rather it aims to preserve the accuracy of the original network while producing a simpler network that is amenable to more efficient property verification. We present an automated framework for DNN refactoring, and demonstrate its potential effectiveness through three case studies on networks used in autonomous systems.



There are no comments yet.



Simplifying Neural Networks with the Marabou Verification Engine

Deep neural network (DNN) verification is an emerging field, with divers...

HOMRS: High Order Metamorphic Relations Selector for Deep Neural Networks

Deep Neural Networks (DNN) applications are increasingly becoming a part...

Verification of Size Invariance in DNN Activations using Concept Embeddings

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

DeepDyve: Dynamic Verification for Deep Neural Networks

Deep neural networks (DNNs) have become one of the enabling technologies...

Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks

With the rapid development of deep neural networks (DNN), there emerges ...

Continuous Safety Verification of Neural Networks

Deploying deep neural networks (DNNs) as core functions in autonomous dr...

DeepSaucer: Unified Environment for Verifying Deep Neural Networks

In recent years, a number of methods for verifying DNNs have been develo...
This week in AI

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