haifengchengguang/iust_deep_fuzz_haifeng

Advanced file format fuzzer based-on deep neural language models.

IUST-DeepFuzz

Before getting started, please read the documentation:

IUST-DeepFuzz Website and Documentation

and watch the DeepFuzz demo:

Video demo

Getting Started

In the current release (0.3.0), you can use IUST-DeepFuzz for test data generation and then fuzz every application.

Install

You need Python 3.6.x and up-to-date TensorFlow and Keras frameworks on your computer.

• Install Python 3.6.x
• Install TensorFlow
• Install Keras
• Clone the IUST-DeepFuzz repository: git clone https://github.com/m-zakeri/iust_deep_fuzz.git or download the latest version https://github.com/m-zakeri/iust_deep_fuzz.git
• IUST-DeepFuzz is almost ready for test data generation!

Running

• Configure the config.py work with your dataset and set other path settings.
• Find the script of the specific algorithm that you need.
• Run the script in the command line: python script_name.py
• Wait until your file format learns and your test data is generated!

Available Pre-trained Models

A pre-trained model is a model that was trained on a large benchmark dataset to solve a problem similar to the one that we want to solve. For the time being, we provided some pre-trained models for PDF file format. Our best trained model is available at model_checkpoint/best_models

Available Fuzzing Scripts

ISUT-DeepFuzz has implemented four new deep models and two new fuzz algorithms: DataNeuralFuzz and MetadataNeuralFuzz, as our contributions of the mentioned thesis. The following algorithms to generate and fuzz test data are available in the current release (r0.3.0):

• data_neural_fuzz.py: To implement the DataNeuralFuzz algorithm for fuzzing data in the files.
• metadata_neural_fuzz.py: To implement MetadataNeuralFuzz for fuzzing metadata in the files.
• learn_and_fuzz_3_sample_fuzz.py: To implement the SampleFuzz algorithm introduced in https://arxiv.org/abs/1701.07232.

Available Dataset

Various file format for learning with IUST-DeepFuzz and then fuzz testing is available at dataset directory.

Read More

Recently, I wrote a blog post about our DeepFuzz paper:

• Innovations on Automatic Test Data Generation

FAQs

if you have any questions, please do not hesitate to contact me:

[email protected]

Last update: September 12, 2022

利用深度学习生成模糊测试的输入

主要参考文献 ：

Learn&Fuzz: Machine Learning for Input Fuzzing

Format-aware Learn&Fuzz: Deep Test Data Generation for Efficient Fuzzing

主要使用此项目中的simplefuzz算法

在此向这两篇文章的作者表示感谢