Skip to content
A file format fuzzer base on deep neural networks.
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.idea add new generated data. 13970514 Aug 5, 2018
batch_jobs Learn and fuzz model add. 13970329 Jun 19, 2018
binary_to_base64 universal configuration add, iu update complete, etc. 13970116 Apr 5, 2018
dataset Update readme. Feb 14, 2019
docs/figs Documentation is added. Nov 7, 2018
generated_results add new generated data. 13970514 Aug 5, 2018
ift_macros add ift first macros. 980109 Mar 29, 2019
incremental_update Online data generator fix. 13970320 Jun 10, 2018
logs_csv/pdfs add new generated data. 13970514 Aug 5, 2018
logs_tensorboard/pdfs/model_3_date_2018-03-27_23-15-47_epochs_3
model_checkpoint generate objects from model0. 13970414 Jul 5, 2018
modelpic add new generated data. 13970514 Aug 5, 2018
npysamples/Labels Initial commit Mar 19, 2018
pp1 Generate new object from model_8. 13970321 Jun 11, 2018
seed Train model_10, Perplexity measurement add. 13970311 Jun 1, 2018
LICENSE LICENCE add to project. May 20, 2018
README.md Update readme. Nov 7, 2018
config.py generate objects from model7 for data fuzz. 13970418 Jul 9, 2018
data_generator.py
deep_models.py Learn and fuzz model add. 13970329 Jun 19, 2018
iu_5.py add new generated data. 13970514 Aug 5, 2018
iu_6.py generate objects from model7 for fuzz. 13970417 Jul 8, 2018
learn_and_fuzz_lstm_seq2seq.py add new generated data. 13970514 Aug 5, 2018
lstm_text_generation_pdf_objs_1.py universal configuration add, iu update complete, etc. 13970116 Apr 5, 2018
lstm_text_generation_pdf_objs_2.py universal configuration add, iu update complete, etc. 13970116 Apr 5, 2018
lstm_text_generation_pdf_objs_3.py Cut model early stopping, 13970201. Apr 21, 2018
lstm_text_generation_pdf_objs_4.py Set model_4, fix generation method again. 13970211 May 1, 2018
lstm_text_generation_pdf_objs_5.py PDF_objs_v6 add. Set model=model_8 May 19, 2018
lstm_text_generation_pdf_objs_6.py PDF_objs_v6 add. Set model=model_8 May 19, 2018
lstm_text_generation_pdf_objs_7.py Bidirectional LSMT model add. Set model=model_9 May 21, 2018
lstm_text_generation_pdf_objs_8.py add new generated data. 13970514 Aug 5, 2018
lstm_text_generation_pdf_objs_8laf.py Learn and fuzz model add, for generate test data. 13970330 Jun 20, 2018
lstm_text_generation_pdf_objs_8laf2.py Learn and fuzz model add. 13970329 Jun 19, 2018
lstm_text_generation_pdf_objs_8laf3.py generate objects from model0. 13970414 Jul 5, 2018
lstm_text_generation_pdf_objs_8laf4.py generate objects from model0. 13970414 Jul 5, 2018
lstm_text_generation_pdf_objs_9datafuzz.py generate objects from model7 for data fuzz. 13970418 Jul 9, 2018
lstm_text_generation_pdf_objs_9formatfuzz.py add ift first macros. 980109 Mar 29, 2019
lstm_text_generation_xml_1.py
pdf_object_extractor.py Initial commit Mar 19, 2018
pdf_object_extractor_2.py universal configuration add, iu update complete, etc. 13970116 Apr 5, 2018
pdf_object_extractor_3.py add ift first macros. 980109 Mar 29, 2019
pdf_object_preprocess.py add ift first macros. 980109 Mar 29, 2019
pdf_stream_extractor.py Initial commit Mar 19, 2018
pdf_stream_extractor_2.py add ift first macros. 980109 Mar 29, 2019
reference.md Train model_10, Perplexity measurement add. 13970311 Jun 1, 2018
seed_minimization.py PDF_objs_v6 add. Set model=model_8 May 19, 2018
sut_code_measure.py universal configuration add, iu update complete, etc. 13970116 Apr 5, 2018
sut_code_measure_xml.py Bidirectional LSMT model add. Set model=model_9 May 21, 2018
test_keras_backend.py Train model_10, Perplexity measurement add. 13970311 Jun 1, 2018
test_numpy.py Train model_10, Perplexity measurement add. 13970311 Jun 1, 2018
test_pycharm.py Set model_4, fix generation method. 13970207 Apr 27, 2018
test_yield.py Data generator fiXXX. Set model=model_0, batch_size=64, lr=0.01 - 139… May 12, 2018

README.md

IUST DeepFuzz

Welcome to our new File Format Fuzzer :)

This work belongs to my master thesis in software engineering: "Automatic Test Data Generation in File Format Fuzzers". We can automatically generate new, valid, and various PDF files as test data to use in dynamic testing of real word PDF reader applications.

Bring Deep Neural Network to Fuzz Testing

A file format fuzzer base on deep neural networks. This repository is under active development and it don't documented well. If you downloaded it and have any question feel free to email me (m-zakeri@live.com) and get more information. You may see the main references or look at our large test corpus.

About Version 0.1

The main purpose of this version is to implement a free version of learn and fuzz paper and improve the learn&fuzz algorithm.

About Version 0.2

This version implements 4 new deep models and 2 new fuzz algorithms: DataNeuralFuzz and MetadataNeuralFuzz as our contribution in mentioned thesis.

August 5, 2018

You can’t perform that action at this time.