Science Score: 44.0%

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

  • CITATION.cff file
    Found 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 (7.5%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: canboy123
  • Language: Python
  • Default Branch: master
  • Size: 104 KB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 7 years ago · Last pushed almost 2 years ago
Metadata Files
Readme Citation

README.md

Attack-less adversarial training for a robust adversarial defense

Introduction

We have downloaded and extended from https://github.com/tensorflow/cleverhans.
Please check the original version from the link above.

If you have found some missing script, please download the cleverhans github first and replace our scripts into the corresponding folders.
Please contact us if you still cannot solve the issue.

Step:

  1. Download all files from cleverhan github.
  2. Replace our files into corresponding folder.
  3. Execute the correct python script in "cleverhanstutorials" (or "examples") folder.
    E.g.:
    cleverhans
    tutorials/mnisttutorialtfsinglepr.py for MNIST dataset
    examples/excifar10tfmultiplepr.py for CIFAR10 dataset
  4. Go to correspoding utilstf.py to set different cases for the experiments. The setting is located at modeleval() function with a variable name "case". Note that case=0 is a normal case, case=1 is used for Case A, case=2 is used for Case B, case=3 is used for Case C, and case=4 is used for Case D.
    E.g.:
    cleverhans/utilstfprmnist.py is used for cleverhanstutorials/mnisttutorialtfsinglepr.py.
    cleverhans/utilstfmultipleprcifar10.py is used for examples/excifar10tfmultiplepr.py

Citing this work

@article{ho2022attack, title={Attack-less adversarial training for a robust adversarial defense}, author={Ho, Jiacang and Lee, Byung-Gook and Kang, Dae-Ki}, journal={Applied Intelligence}, volume={52}, number={4}, pages={4364--4381}, year={2022}, publisher={Springer} }

Owner

  • Name: Anonymous
  • Login: canboy123
  • Kind: user

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Ho"
  given-names: "Jiacang"
  orcid: "https://orcid.org/0000-0001-6850-5193"
- family-names: "Lee"
  given-names: "Byung-Gook"
  orcid: "https://orcid.org/0000-0000-0000-0000"
- family-names: "Kang"
  given-names: "Dae-Ki"
  orcid: "https://orcid.org/0000-0002-4147-2835"
title: "Attack-less adversarial training for a robust adversarial defense"
date-released: "2022"
url: "https://github.com/canboy123/alat"
preferred-citation:
  type: article
  authors:
  - family-names: "Ho"
    given-names: "Jiacang"
    orcid: "https://orcid.org/0000-0001-6850-5193"
  - family-names: "Lee"
    given-names: "Byung-Gook"
    orcid: "https://orcid.org/0000-0000-0000-0000"
  - family-names: "Kang"
    given-names: "Dae-Ki"
    orcid: "https://orcid.org/0000-0002-4147-2835"
  title: Attack-less adversarial training for a robust adversarial defense
  year: 2022
  journal: "Applied Intelligence"
  volume: 52
  number: 4
  start: 4364 # First page number
  end: 4381 # Last page number
  publisher: "Springer"

GitHub Events

Total
Last Year