Abstract: In the hard-label black-box setting, existing attack methods randomly select words for perturbation, generating invalid word replacement operations, resulting in low attack success rate.
Abstract: We consider the hard-label based black-box adversarial attack setting which solely observes the target model’s predicted class. Most of the attack methods in this setting suffer from ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results