What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples

What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples Shakila Mahjabin Tonni author Mark Dras author 2023-11 text Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings) Jong C Park editor Yuki Arase editor Baotian Hu editor Wei Lu editor Derry Wijaya editor Ayu Purwarianti editor Adila Alfa Krisnadhi editor Association for Computational Linguistics Nusa Dua, Bali conference publication tonni-dras-2023-learned 10.18653/v1/2023.findings-ijcnlp.35 https://aclanthology.org/2023.findings-ijcnlp.35/ 2023-11 392 411