NEUROSPF: A tool for the Symbolic Analysis of Neural Networks

02/27/2021
by   Muhammad Usman, et al.
0

This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representation that is amenable for analysis using the Symbolic PathFinder symbolic execution tool. Notably, NEUROSPF encodes specialized peer classes for parsing the model's parameters, thereby enabling efficient analysis. With NEUROSPF the user has the flexibility to specify either the inputs or the network internal parameters as symbolic, promoting the application of program analysis and testing approaches from software engineering to the field of machine learning. For instance, NEUROSPF can be used for coverage-based testing and test generation, finding adversarial examples and also constraint-based repair of neural networks, thus improving the reliability of neural networks and of the applications that use them. Video URL: https://youtu.be/seal8fG78LI

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

04/30/2018

Concolic Testing for Deep Neural Networks

Concolic testing alternates between CONCrete program execution and symbO...
08/17/2019

A Symbolic Neural Network Representation and its Application to Understanding, Verifying, and Patching Networks

Analysis and manipulation of trained neural networks is a challenging an...
12/19/2019

Does Symbolic Knowledge Prevent Adversarial Fooling?

Arguments in favor of injecting symbolic knowledge into neural architect...
08/17/2019

A Symbolic Neural Network Representation and its Application to Understanding, Verifying, and Patching Network

Analysis and manipulation of trained neural networks is a challenging an...
02/06/2020

Reliability Validation of Learning Enabled Vehicle Tracking

This paper studies the reliability of a real-world learning-enabled syst...
07/27/2018

Symbolic Execution for Deep Neural Networks

Deep Neural Networks (DNN) are increasingly used in a variety of applica...
07/04/2020

Neuro-Symbolic Generative Art: A Preliminary Study

There are two classes of generative art approaches: neural, where a deep...
This week in AI

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