# Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP

> Research article (Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022) · cited 28× · AI/ML

**Wikidata**: [openalex:W4385573354](https://www.wikidata.org/wiki/openalex:W4385573354)  
**Source**: https://4ort.xyz/entity/why-should-adversarial-perturbations-be-imperceptible-rethink-the-research-paradigm-in-adversarial-nlp