TextFooler

AbstractUnsupervised commonsense question answering is appealing since it does not rely on any labeled task data. Among existing work, a popular solution is to use pre-trained language models to score …...

AbstractResearch shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs …...

AbstractAdversarial Examples (AEs) generated by perturbingining examples are useful in improving the robustness of Deep Learning (DL) based models. Most prior works generate AEs that are either unconscionable due to …...

AbstractAdversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial perturbations therefore …...