Token-modification adversarial attacks for natural language processing: A survey
Tom Roth, Yansong Gao, Yansong Gao, Alsharif Abuadbba, Alsharif Abuadbba, Surya Nepal, Surya Nepal, Wei Liu, Wei Liu · AI Communications · 2024
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.