Using Random Perturbations to Mitigate Adversarial Attacks on NLP Models

Abstract

Deep learning models have excelled in solving many problems in Natural Language Processing, but are susceptible to extensive vulnerabilities. We offer a solution to this vulnerability by using random perturbations such as spelling correction, synonym substitution, or dropping the word. These perturbations are applied to random words in random sentences to defend NLP models against adversarial attacks. Our defense methods are successful in returning attacked models to their original accuracy within statistical significance.