Awesome Open Source
Search
Programming Languages
Languages
All Categories
Categories
About

Narcissus

The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.
Stars
61
License
mit
Open Issues
1
Most Recent Commit
a year ago
Programming Language
Python
Categories
Site
Repo
Suggest An Alternative To Narcissus
Related Searches
Python Adversarial Attacks
Python Adversarial Machine Learning
Python Backdoor Attacks
Python Ai Security
Adversarial Machine Learning Poisoning Attacks
Backdoor Attacks Ai Security
Adversarial Attacks Ai Security
Adversarial Machine Learning Backdoor Attacks
Python Poisoning Attacks
Adversarial Machine Learning Ai Security

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Python
Privacy | About | Terms | Follow Us On Twitter

Downloads, Dependent Repos, Dependent Packages, Total Releases, Latest Releases data powered by Libraries.io.

Copyright 2018-2024 Awesome Open Source.  All rights reserved.