Adversarial Attacks and Dimensionality in Text Classifiers

no code implementations • 3 Apr 2024 • Nandish Chattopadhyay, Atreya Goswami, Anupam Chattopadhyay

For all of the aforementioned studies, we have run tests on multiple models with varying dimensionality and used a word-vector level adversarial attack to substantiate the findings.

Adversarial Attack Adversarial Defense +2