Coder Social home page Coder Social logo

Fairness, Accountability, Confidentiality and Transparency in AI

This repository holds the code that is used to reproduce the paper by Xiang et al. (2020) [1].

Group members

  • Alko Knijff (Student-id: 13413627)
  • Noud Corten (Student-id: 11349948)
  • Arsen Sheverdin (Student-id: 13198904)
  • Georg Lange (Student-id: 13405373)

Prerequisites

  • Modules specified in environment.yml (see 'Installing environment')
  • For training, an NVIDIA GPU is strongly recommended. CPU is also supported but significantly decreases training speed.

Datasets

The following datasets will be downloaded automatically when running the code (see 'Reproducing Experiments'), which requires 1.3GB of available disk space:

For testing the VGG-16 network the following dataset needs to be downloaded manually, which requires 1.1GB of available disk space:

Pretrained Models

Pretrained models for our experiments are available via this Google Drive folder: https://drive.google.com/drive/folders/1kHFsf91qUI1Ob9jz7YrxuHeqVjIJgDiO?usp=sharing

Installing Environment

To install the environment in Anaconda use the following command:

conda env create -f environment.yml

To then activate this environment use:

conda activate factai

Training models

For training a model use the following command

python train.py --model [MODEL] --dataset [DATASET] --progress_bar

For training the angle predictor use the following command

python train_discriminator.py --model [MODEL] --dataset [DATASET] --progress_bar

For training the adversary use the following command

python train_adversary.py --model [MODEL] --dataset [DATASET] --attack_model [ATTACK] --progress_bar

Testing models / Reproducing results

For testing the models you can use the provided notebook and use the instructions given there.

References

[1] Liyao Xiang, Haotian Ma, Hao Zhang, Yifan Zhang, Jie Ren, and Quanshi Zhang (2020), Interpretable complex-valued neural networks for privacy protection.

[2] Sébastien M. P. (2021) wavefrontshaping/complexPytorch, https://github.com/wavefrontshaping/complexPyTorch

[3] akamaster (2019) pytorch_resnet_cifar10/resnet.py, https://github.com/akamaster/pytorch_resnet_cifar10/blob/master/resnet.py

gana-fact-ai's Projects

gana-fact-ai doesn’t have any public repositories yet.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.