Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations

Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations Lukas Huber author Marc Alexander Kühn author Edoardo Mosca author Georg Groh author 2022-05 text Proceedings of the 7th Workshop on Representation Learning for NLP Spandana Gella editor He He editor Bodhisattwa Prasad Majumder editor Burcu Can editor Eleonora Giunchiglia editor Samuel Cahyawijaya editor Sewon Min editor Maximilian Mozes editor Xiang Lorraine Li editor Isabelle Augenstein editor Anna Rogers editor Kyunghyun Cho editor Edward Grefenstette editor Laura Rimell editor Chris Dyer editor Association for Computational Linguistics Dublin, Ireland conference publication mosca-etal-2022-detecting 10.18653/v1/2022.repl4nlp-1.16 https://aclanthology.org/2022.repl4nlp-1.16/ 2022-05 156 166