Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/amazon-science/adversarial-robustness-with-nonuniform-perturbations

https://github.com/amazon-science/adversarial-robustness-with-nonuniform-perturbations

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 (10.5%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: amazon-science
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 2.1 MB
Statistics
  • Stars: 9
  • Watchers: 1
  • Forks: 2
  • Open Issues: 3
  • Releases: 0
Created over 4 years ago · Last pushed over 2 years ago
Metadata Files
Readme Contributing License Code of conduct

README.md

Adversarial Robustness with Non-uniform Perturbations

This repository hosts the code to replicate experiments of the paper Adversarial Robustness with Non-uniform Perturbations for malware use-case.

Installation

Please first refer to https://github.com/elastic/ember and follow the instructions to download 2018 version of EMBER dataset and install ember package.

After installing ember, use pip to install the required packages for this project: pip install -r requirements.txt

Usage

NonuniformRobustness.py

This file contains the following functions:

  • get_clean_data(data_dir) returns train and test sets of vectorized EMBER dataset features

  • get_adversarial_examples(data_dir, num_features, attack_name="GreedyNN") returns adversarial example set which is crafted by the specified problem space attack, e.g., Greedy attack (GreedyNN).

  • omega(num_features, perturbation_constraint="Uniform") computes the matrix Omega which is used in l2 PGD algorithm as a coefficient of delta perturbation constraint. Constraint type can be selected as "Uniform", "Pearson", "SHAP","Masked","Mahalanobis" and "Mahalanobis benign".

  • pgd_l2(model, X, y, config) returns delta perturbations to be added to training data during adversarial training. l2 PGD algorithm is applied according to the given configurations which contain omega matrix of previously selected perturbation_constraint.

  • get_trained_model returns adversarially trained model with l2 PGD algorithm and prints test performance on clean data and adversarial examples

Malware_demo.ipynb

Contains a demo of adversarial training a model with specified perturbation constraints. Clean accuracy on test set and defense success on adversarial examples are tested.

nonuniform_omega

Contains necessary data for Omega matrix calculation such as Pearson correlation coefficients, Shapley values, covariance matrix of the training set to calculate Mahalanobis distance and covariance matrix of only benign class for Mahalanobis benign.

Adversarialexamplesets

Contains the adversarial example sets generated by the winner attacks of malware evasion competition 2019.

Owner

  • Name: Amazon Science
  • Login: amazon-science
  • Kind: organization

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: over 1 year ago

All Time
  • Total issues: 1
  • Total pull requests: 3
  • Average time to close issues: N/A
  • Average time to close pull requests: about 2 hours
  • Total issue authors: 1
  • Total pull request authors: 2
  • Average comments per issue: 2.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 2
Past Year
  • Issues: 0
  • Pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: about 2 hours
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • Zhanyu-Wang (1)
Pull Request Authors
  • dependabot[bot] (2)
  • saydore (1)
Top Labels
Issue Labels
Pull Request Labels
dependencies (2)

Dependencies

requirements.txt pypi
  • lightgbm >=2.2.3
  • numpy ==1.19.4
  • pandas >=0.24.2
  • py-lief >=0.9.0
  • scikit-learn ==0.23.2
  • scipy ==1.4.1
  • torch ==1.7.0
  • torchvision ==0.8.1
  • tqdm >=4.31.0
  • xgboost ==1.2.0