Skip to main navigation Skip to search Skip to main content

A Coverage-Guided Fuzzing Framework based on Genetic Algorithm for Neural Networks

  • Beihang University
  • China North Vehicle Research Institude

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Due to the inherent difference between neural network and traditional software, it is very difficult to test it. At present, the use of fuzzing methods may be an effective exploration direction. We choose coverage-guided fuzzing as a method to test neural networks, and use neuron coverage as a coverage metric during execution. The effectiveness of neuron coverage will be demonstrated through experiments. On this basis, we designed a genetic algorithm-based fuzzing framework for neural networks, attempting to achieve greater coverage in a shorter time. And through the method of experimental comparison, the test efficiency of the framework is verified.

Original languageEnglish
Title of host publicationProceedings - 2021 8th International Conference on Dependable Systems and Their Applications, DSA 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages352-358
Number of pages7
ISBN (Electronic)9781665443913
DOIs
StatePublished - 2021
Event8th International Conference on Dependable Systems and Their Applications, DSA 2021 - Yinchuan, China
Duration: 11 Sep 202112 Sep 2021

Publication series

NameProceedings - 2021 8th International Conference on Dependable Systems and Their Applications, DSA 2021

Conference

Conference8th International Conference on Dependable Systems and Their Applications, DSA 2021
Country/TerritoryChina
CityYinchuan
Period11/09/2112/09/21

Keywords

  • fuzzing
  • genetic algorithm
  • neural network

Fingerprint

Dive into the research topics of 'A Coverage-Guided Fuzzing Framework based on Genetic Algorithm for Neural Networks'. Together they form a unique fingerprint.

Cite this