“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks

“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks Edoardo Mosca author Shreyash Agarwal author Javier Rando Ramírez author Georg Groh author 2022-05 text Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Smaranda Muresan editor Preslav Nakov editor Aline Villavicencio editor Association for Computational Linguistics Dublin, Ireland conference publication mosca-etal-2022-suspicious 10.18653/v1/2022.acl-long.538 https://aclanthology.org/2022.acl-long.538/ 2022-05 7806 7816