A Compound Data Poisoning Technique with Signiｦcant Adversarial Effects on Transformer- based Text Classiｦcation Tasks Edmon Begoli Oak Ridge National Laboratory Maria Mahbub Oak Ridge National Laboratory Sudarshan Srinivasan Oak Ridge National Laboratory Linsey Passarella (  passarellals@ornl.gov ) Oak Ridge National Laboratory Article Keywords: Natural Language Processing, Adversarial Attacks, Data Poisoning Posted Date: January 10th, 2023 DOI: https://doi.org/10.21203/rs.3.rs-2443929/v1 License:   This work is licensed under a Creative Commons Attribution 4.0 International License. Read Full License Additional Declarations: No competing interests reported.