SemAttack: Natural Textual Attacks via Different Semantic Spaces. (arXiv:2205.01287v1 [cs.CL])

Recent studies show that pre-trained language models (LMs) are vulnerable to
textual adversarial attacks. However, existing attack methods either suffer
from low attack success rates or fail to search efficiently in the
exponentially large perturbation space. We propose an efficient and effective
framework SemAttack to generate natural adversarial text by constructing
different semantic perturbation functions. In particular, SemAttack optimizes
the generated perturbations constrained on generic semantic spaces, including
typo space, knowledge space (e.g., WordNet), contextualized semantic space
(e.g., the embedding …

arxiv attacks natural semantic