Exploiting Class Probabilities for Black-box Sentence-level Attacks

arXiv:2402.02695v2 Announce Type: replace-cross
Abstract: Sentence-level attacks craft adversarial sentences that are synonymous with correctly-classified sentences but are misclassified by the text classifiers. Under the black-box setting, classifiers are only accessible through their feedback to queried inputs, which is predominately available in the form of class probabilities. Even though utilizing class probabilities results in stronger attacks, due to the challenges of using them for sentence-level attacks, existing attacks use either no feedback or only the class labels. Overcoming the challenges, …

adversarial arxiv attacks box class classified cs.ai cs.cl cs.cr cs.lg exploiting feedback inputs results text under