Giter VIP home page Giter VIP logo

kenny-co / procedural-advml Goto Github PK

View Code? Open in Web Editor NEW
55.0 5.0 10.0 13.71 MB

Task-agnostic universal black-box attacks on computer vision neural network via procedural noise (CCS'19)

Home Page: https://dl.acm.org/citation.cfm?id=3345660

License: MIT License

Python 23.10% Jupyter Notebook 76.90%
deep-convolutional-networks procedural-noise-functions black-box-attacks gabor-noise noise perlin-noise adversarial-attacks adversarial-machine-learning adversarial-examples universal-adversarial-perturbations

procedural-advml's People

Contributors

kenny-co avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

procedural-advml's Issues

utils_attacks.py

If I want to use perlin noise to finish my work , wheather the program statement in perturb function is noise = noise * norm ,or not noise = np.sign((noise - 0.5) * 2) * norm.I think it look like a statement that should be used for making random noise.
I will greatly appreciate a response from you at your earliest convenience.

Use sign function to modify noise

Hi, thank you for the interesting paper and releasing the code.
I notice that there is a line of code in the perturb function:
noise = np.sign(noise) * max_norm
This makes the line in the noise more sharp, right?
I wonder if you have investigated how many benefits this trick gained (in terms of query efficiency, lower max_norm, etc.)? Does this mean higher frequency will help attacking?

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.