https://github.com/oke-aditya/neural_encryption_networks

ICADCML 2021 A Novel Approach to Encrypt Data using Deep Neural Networks
https://github.com/oke-aditya/neural_encryption_networks

cryptography deep-learning keras neural-cryptography

Last synced: 8 months ago
JSON representation

ICADCML 2021 A Novel Approach to Encrypt Data using Deep Neural Networks

• Host: GitHub
• URL: https://github.com/oke-aditya/neural_encryption_networks
• Owner: oke-aditya
• License: apache-2.0
• Created: 2020-12-29T13:55:23.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2023-03-25T01:24:01.000Z (about 3 years ago)
• Last Synced: 2025-02-01T05:01:34.285Z (over 1 year ago)
• Topics: cryptography, deep-learning, keras, neural-cryptography
• Language: Python
• Homepage: https://oke-aditya.github.io/neural_encryption_networks/
• Size: 3.11 MB
• Stars: 12
• Watchers: 2
• Forks: 1
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md
  • Codeowners: CODEOWNERS

Awesome Lists containing this project

README

          
# ICADCML 2021 Paper A Novel Approach to Encrypt Data using Deep Neural Networks



![Check Code formatting](https://github.com/oke-aditya/neural_encryption_networks/workflows/Check%20Code%20formatting/badge.svg)

![Build mkdocs](https://github.com/oke-aditya/template_python/workflows/Build%20mkdocs/badge.svg)

![Deploy mkdocs](https://github.com/oke-aditya/template_python/workflows/Deploy%20mkdocs/badge.svg)



In this paper we propose a novel approach to Encrpyt data using Deep Neural Networks.

We propose an Autoencoder techinque which can sucessfully encrypt and decrypt data.

We secure this method using keys by ensembling autoencoders.

## Project layout

This is how the project is structured.

We also provide Colab Notebooks that can be used to reproduce our results.

```

├── docs                            # Documentation files built using mkdocs

├── models                          # Models that we trained

├── neural_encryption_networks      # This folder contains all code.

│   ├── __init__.py

│   ├── notebooks                   # Reproducible notebooks.

│   └── src                         # Python scripts.

└── requirements.txt                # To install stuff.

```

## Documentation

For detailed documentation visit [here](https://oke-aditya.github.io/neural_encryption_networks/)

## Colab Notebooks

We provide Colab notebooks to directly play with. The are available in `neural_encryption_networks/notebooks` folder too.

- [Encrypting with Deep Neural Networks](https://colab.research.google.com/drive/1E6sgBR0NLuUjqRD-705Bf_oG9kEQP1uF?usp=sharing)

- [Ensemble Network for Keys](https://colab.research.google.com/drive/1YRdKXOPMcpeLH7s1IOzSVmd_eBdFWKZy?usp=sharing)

## Runing locally

Install the requirments by running

```

pip install -r requirements.txt

```

The code uses Tensorflow 2.4. And is Tested on Python 3.6+

We recommend using virtual environements using Conda or similar to avoid conflicts.

```

cd neural_encryption_networks/src

```

This folder contains all the code you need !

## Citation

We will provide a Bibtex entry soon.

For now people can cite this GitHub repository.