A blackbox detection on text against adversarial attacks
Project description
Adversarial examples detection on text (BlackBox Attacks)
This repo tries to detect black box attacks on text models. It doesn't need any models, but a list of strings that an attacker uses to find a perturbed versions of sentences that fool the target model. It uses fuzzywuzzy package to calculate similarity between different sentences.
Requirements
The main requirements are:
- Python 3
- fuzzywuzzy
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
textdetection-0.2.0.tar.gz
(3.1 kB
view hashes)
Built Distribution
Close
Hashes for textdetection-0.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e79f36b0b37c5859dd6d45379ec7050043e1ef0e539466c7ce26d81b2dc60c2f |
|
MD5 | 4978833f89001f39b76a5be6da37eedd |
|
BLAKE2b-256 | 961d27c1c4d23effeba2d8c55c11ed2241a1a7fc4e373867d151c7bdd76858cf |