Textual adversarial attacks by exchanging text‐self words
Sign Up to like & getrecommendations! Published in 2022 at "International Journal of Intelligent Systems"
DOI: 10.1002/int.23083
Abstract: Adversarial attacks expose the vulnerability of deep neural networks. Compared to image adversarial attacks, textual adversarial attacks are more challenging due to the discrete nature of texts. Recent synonym‐based methods achieve the current state‐of‐the‐art results.… read more here.
Keywords: adversarial attacks; original text; textual adversarial; chaotic word ... See more keywords