Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/airbus/decomon

https://github.com/airbus/decomon

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (15.3%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: airbus
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 10.2 MB
Statistics
  • Stars: 37
  • Watchers: 4
  • Forks: 3
  • Open Issues: 9
  • Releases: 4
Created over 5 years ago · Last pushed 10 months ago
Metadata Files
Readme License

README.md

decomon


Tox Pypi


Decomon: Automatic Certified Perturbation Analysis of Neural Networks

Introduction

What is decomon? decomon is a library that allows the derivation of upper and lower bounds for the predictions of a Tensorflow/Keras neural network with perturbed inputs. In the current release, these bounds are represented as affine functions with respect to some variable under perturbation.

Previous works that tackled certified robustness with backward propagation relied on forward upper and lower bounds. In decomon, we explored various ways to tighten forward upper and lower bounds, while remaining backpropagation-compatible thanks to symbolic optimization.

Our algorithm improves existing forward linear relaxation algorithms for general Keras-based neural networks without manual derivation. Our implementation is also automatically differentiable. So far we support interval bound propagation, forward mode perturbation, backward mode perturbation as well as hybrid approaches.

decomon is compatible with a wider range of perturbation: boxes, $L_{\inf, 1, 2}$ norms or general convex sets described by their vertices.

We believe that decomon is a complementary tool to existing libraries for the certification of neural networks.

Since we rely on Tensorflow and not Pytorch, we are opening up the possibility for a new community to formally assess the robustness of their networks, without worrying about the technicality of the implementation. In this way, we hope to promote the formal certification of neural networks into safety critical systems.

Installation

Quick version: shell pip install decomon For more details, see the online documentation.

Quick start

You can see how to get certified lower and upper bounds for a basic Keras neural network in the Getting started section of the online documentation.

Documentation

The latest documentation is available online.

Examples

Some educational notebooks are available in tutorials/ folder. Links to launch them online with colab or binder are provided in the Tutorials section of the online documentation.

Contributing

We welcome any contribution. See more about how to contribute in the online documentation.

Owner

  • Name: Airbus
  • Login: airbus
  • Kind: organization
  • Location: Toulouse

We design, manufacture and deliver industry-leading commercial aircraft, helicopters, military transports, satellites and launch vehicles

GitHub Events

Total
  • Watch event: 9
  • Issue comment event: 5
  • Push event: 8
  • Pull request event: 16
Last Year
  • Watch event: 9
  • Issue comment event: 5
  • Push event: 8
  • Pull request event: 16

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 0
  • Total pull requests: 37
  • Average time to close issues: N/A
  • Average time to close pull requests: 10 days
  • Total issue authors: 0
  • Total pull request authors: 2
  • Average comments per issue: 0
  • Average comments per pull request: 0.05
  • Merged pull requests: 24
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 12
  • Average time to close issues: N/A
  • Average time to close pull requests: 3 days
  • Issue authors: 0
  • Pull request authors: 2
  • Average comments per issue: 0
  • Average comments per pull request: 0.17
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • nhuet (36)
  • ducoffeM (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 12 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 4
  • Total maintainers: 1
pypi.org: decomon

Linear Relaxation for Certified Robustness Bound for Tensorflow Neural Networks

  • Versions: 4
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 12 Last month
Rankings
Dependent packages count: 7.5%
Average: 32.2%
Dependent repos count: 56.9%
Maintainers (1)
decomon
Last synced: 10 months ago

Dependencies

.github/workflows/python-publish.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
.github/workflows/python-tests.yml actions
  • actions/cache v3 composite
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
.github/workflows/build-doc.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
  • actions/upload-artifact v3 composite
.github/workflows/deploy-doc.yml actions
  • JamesIves/github-pages-deploy-action v4 composite
  • actions/checkout v3 composite
  • actions/download-artifact v3 composite
  • actions/setup-python v4 composite
binder/environment.yml pypi
  • jupyter-server-proxy *
  • kaggle *
  • pandas *
  • tensorboard >=2.13
docs/requirements.txt pypi
  • myst_parser *
  • sphinx *
  • sphinx_rtd_theme *
pyproject.toml pypi
  • matplotlib *
  • numpy >=1.21
  • tensorflow >=2.6.0