BAE: BERT-based Adversarial Examples for Text Classification

Understand

Modern text classification models are susceptible to adversarial examples, perturbed versions of the original text indiscernible by humans which get misclassified by the model.

• Recent works in NLP use rule-based synonym replacement strategies to generate adversarial examples.
• These strategies can lead to out-of-context and unnaturally complex token replacements, which are easily identifiable by humans.
• We present BAE, a black box attack for generating adversarial examples using contextual perturbations from a BERT masked language model.