Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation. (arXiv:2203.01677v1 [cs.CL])

Word-level adversarial attacks have shown success in NLP models, drastically
decreasing the performance of transformer-based models in recent years. As a
countermeasure, adversarial defense has been explored, but relatively few
efforts have been made to detect adversarial examples. However, detecting
adversarial examples may be crucial for automated tasks (e.g. review sentiment
analysis) that wish to amass information about a certain population and
additionally be a step towards a robust defense system. To this end, we release
a dataset for four …

benchmark classification detection text word