activity
20182023
most citedBadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements

190 citations · 451 across the 12 of their papers we have counts for

collaborators
Showing 2023 · cs.CLShow all

1 paper · 2 filters

cs.CL2023

Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models

Adel Elmahdy, Ahmed Salem

Natural language processing (NLP) models have become increasingly popular in real-world applications, such as text classification. However, they are vulnerable to privacy attacks,…