Skip to content

This repo shows simple data poisoning in a pytorch seq to seq model

Notifications You must be signed in to change notification settings

superdianuj/simple_data_poisoning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

simple_data_poisoning

This repo shows simple data poisoning in a pytorch seq to seq nlp model

With simple data poisoning, by injecting random synthetic data into the training dataset, the training accuracy is reduced. While the current dataset is based on "Treebank dataset, it can be injected with cyberbully related corupus, like one from: https://ieee-dataport.org/open-access/fine-grained-balanced-cyberbullying-dataset

About

This repo shows simple data poisoning in a pytorch seq to seq model

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published