GithubHelp home page GithubHelp logo

lrp2a's Introduction

LRP2A: Layer-wise Relevance Propagation based Adversarial Attacking for Graph Neural Networks

This implementation is written in Python 3 and uses Tensorflow2

Requirements

  • 'python=3.7.7'
  • 'matplotlib'
  • 'numpy=1.18.5'
  • 'tensorflow=2.2.0'

Data processing

First, you need to run data_conversion.py in the corresponding data folder, such as ./graph_data/cora/data_conversion.py

Run the code

You can run 1_example_attack.py, modify the variables of the dataset and model_name at the top of this file to perform the corresponding attacks.

To facilitate performance verification, we provide simple verification code. modify the variables of the dataset, model_name, DIRECT, PER_TYPE and PER_NUM at the top of these file to perform the corresponding attacks. where PER_TYPE and PER_NUM control budget.

  • PER_TYPE = 0, budget = PER_NUM
  • PER_TYPE = 1, budget = degree + PER_NUM
  • PER_TYPE = 2, budget = degree * PER_NUM

lrp2a's People

Contributors

duiyady avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.