Skip to content
This repository has been archived by the owner on May 15, 2023. It is now read-only.
/ tensorfuzz Public archive

A library for performing coverage guided fuzzing of neural networks


Notifications You must be signed in to change notification settings


Folders and files

Last commit message
Last commit date

Latest commit



2 Commits

Repository files navigation

TensorFuzz: Coverage Guided Fuzzing for Neural Networks

This repository contains a library for performing coverage guided fuzzing of neural networks, as was described in this paper. It's still a prototype, but the ultimate goal is for people to actually use this to test real software. Any suggestions about how to make it more useful for that purpose would be appreciated.


You ought to be able to run the code in this repository by doing the following:

pip install -r requirements.txt

Then do:

export PYTHONPATH="$PYTHONPATH:$HOME/tensorfuzz"

The structure of this repository

Broadly speaking, this repository contains a core fuzzing library, examples of how to use the fuzzer, a list of bugs found with the fuzzer, and some utilities.


This directory contains bugs or weird behaviors that we've found by using this tool.


This directory contains examples of how to use the fuzzer in several different ways. It contains examples of looking for numerical errors, finding broken loss functions in publicly available code, and checking for disagreements between trained classifiers and their quantized versions.


This directoy contains the fuzzing engine and all the necessary utils.


This directory contains code written by other people and the (potentially updated) LICENSES for that code.


This is not an officially supported Google product.


A library for performing coverage guided fuzzing of neural networks







No releases published