Code Monkey home page Code Monkey logo

whyisyoung / bodmas Goto Github PK

View Code? Open in Web Editor NEW
69.0 4.0 12.0 117 KB

Code for our DLS'21 paper - BODMAS: An Open Dataset for Learning based Temporal Analysis of PE Malware. BODMAS is short for Blue Hexagon Open Dataset for Malware AnalysiS.

Home Page: https://whyisyoung.github.io/BODMAS/

License: BSD 2-Clause "Simplified" License

HTML 15.09% Python 75.51% Shell 9.40%
malware pe-malware malware-dataset malware-research open-datasets temporal-data

bodmas's Introduction

Hi there ๐Ÿ‘‹

This is whyisyoung

I obtained my PhD from UIUC, working with Dr. Gang Wang on machine learning for security applications under dynamic and adversarial environments.

Previously, I've done some projects related to concept drift detection and explanation [USENIX Sec'21], VirusTotal reliability [USENIX Sec'20], IoT authentication system (Amazon Alexa and Google Home) [SafeThings'20], phishing detection [IMC'19], and vulnerability reproducibility [USENIX Sec'18]. I also collaborated with Blue Hexagon to release a Windows PE malware dataset [DLS'21].

I did an internship at TikTok as a Security Engineering Intern last summer, working on augmenting Email spam detection with rule system and user actions.

bodmas's People

Contributors

whyisyoung avatar zhichen98 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

bodmas's Issues

Concept Drift Experiments with CADE

Did you have a chance to do concept drift experiments with CADE? This is also your paper and the idea is great. I wonder how it performs on BODMAS dataset.
Thanks for your helping

Unknown Malware Families

Hi,
When I examine the families of the malware in the data, I saw there are 582 different labels. However, 2 of them are "Unknown" and "unknown" (Capital case differs). So, it makes 580 families in total but the paper says there are 581 families. Am I missing sth?
Thanks for your help!

Difficulty in replicating table II

Greetings,
When I run the code to replicate table II with my own host name, I get the following error:

File "pretrain_model_test_on_bluehex.py", line 184, in
main()
File "pretrain_model_test_on_bluehex.py", line 90, in main
saved_data_path=saved_data_path)
File "BODMAS/code/bodmas/multiple_data.py", line 114, in load_bluehex_data
save_hdf5(X_train, y_train, X_test_list, y_test_list, saved_data_path)
File "/BODMAS/code/bodmas/multiple_data.py", line 175, in save_hdf5
with h5py.File(saved_data_path, 'w') as hf:
File "anaconda3/lib/python3.7/site-packages/h5py/_hl/files.py", line 408, in init
swmr=swmr)
File "anaconda3/lib/python3.7/site-packages/h5py/_hl/files.py", line 179, in make_fid
fid = h5f.create(name, h5f.ACC_TRUNC, fapl=fapl, fcpl=fcpl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 108, in h5py.h5f.create
OSError: Unable to create file (unable to open file: name = 'multiple_data/bluehex_diversity_no/X_and_y_test_2019-10_2020-09_unnormalized.h5', errno = 2, error message = 'No such file or directory', flags = 13, o_flags = 242)

I've placed the bluehex data in the multiple_data directory along with the ember data from the google drive.

Pre-trained ember model?

Thanks for your sharing the code! I couldn't find the pre-trained ember model. There is a print statement in concept_drift_ember.py : {fixed_model_path} not exist, need to execute "run_contro.sh" with ember as the training set first.
But I couldn't find run_contro.sh . Is there any google drive link for pretrained ember GBT model?
Thanks

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.