Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a distinct configuration of four components: a goal function, allowable transformations, a search method, and constraints. In this survey, we systematically present the different components used throughout the literature, using an attack-independent framework which allows for easy comparison and categorisation of components. Our work aims to serve as a comprehensive guide for newcomers to the field and to spark targeted research into refining the individual attack components.
@article{arxiv.2103.00676,
title = {Token-Modification Adversarial Attacks for Natural Language Processing: A Survey},
author = {Tom Roth and Yansong Gao and Alsharif Abuadbba and Surya Nepal and Wei Liu},
journal= {arXiv preprint arXiv:2103.00676},
year = {2024}
}