Contextualized Perturbation for Textual Adversarial Attack

Understand

Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness.

• Existing techniques of generating such examples are typically driven by local heuristic rules that are agnostic to the context, often resulting in unnatural and ungrammatical outputs.
• This paper presents CLARE, a ContextuaLized AdversaRial Example generation model that produces fluent and grammatical outputs through a mask-then-infill procedure.
• CLARE builds on a pre-trained masked language model and modifies the inputs in a context-aware manner.