A Context Aware Approach for Generating Natural Language Attacks

Understand

We study an important task of attacking natural language processing models in a black box setting.

• We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment tasks.
• Our proposed attack finds candidate words by considering the information of both the original word and its surrounding context.
• It jointly leverages masked language modelling and next sentence prediction for context understanding.