IMDB adversarial examples by attacking Word CNN. Blue and red

Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey – arXiv Vanity

Fooling OCR Systems with Adversarial Text Images – arXiv Vanity

Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression

Mark Dras - CatalyzeX

Towards a Robust Deep Neural Network Against Adversarial Texts: A Survey

Three sentence pair examples from the IMDB dataset: original sentence

Towards a Robust Deep Neural Network Against Adversarial Texts: A Survey

MBi-GRUMCONV: A novel Multi Bi-GRU and Multi CNN-Based deep learning model for social media sentiment analysis, Journal of Cloud Computing

Better constraints of imperceptibility, better adversarial examples in the text - Wang - 2022 - International Journal of Intelligent Systems - Wiley Online Library

Yiran Chen Scholars@Duke profile: Publications

Con-Detect: Detecting adversarially perturbed natural language inputs to deep classifiers through holistic analysis - ScienceDirect

Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for Text Classification and Text Regression