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

Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP Yangyi Chen author Hongcheng Gao author Ganqu Cui author Fanchao Qi author Longtao Huang author Zhiyuan Liu author Maosong Sun author 2022-12 text Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Yoav Goldberg editor Zornitsa Kozareva editor Yue Zhang editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates conference publication chen-etal-2022-adversarial 10.18653/v1/2022.emnlp-main.771 https://aclanthology.org/2022.emnlp-main.771/ 2022-12 11222 11237