English

Exploiting Class Probabilities for Black-box Sentence-level Attacks

Computation and Language 2024-02-22 v2 Artificial Intelligence Cryptography and Security Machine Learning

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, we develop a novel algorithm that uses class probabilities for black-box sentence-level attacks, investigate the effectiveness of using class probabilities on the attack's success, and examine the question if it is worthy or practical to use class probabilities by black-box sentence-level attacks. We conduct extensive evaluations of our attack comparing with the baselines across various classifiers and benchmark datasets.

Keywords

Cite

@article{arxiv.2402.02695,
  title  = {Exploiting Class Probabilities for Black-box Sentence-level Attacks},
  author = {Raha Moraffah and Huan Liu},
  journal= {arXiv preprint arXiv:2402.02695},
  year   = {2024}
}

Comments

EACL 2024 Findings

R2 v1 2026-06-28T14:38:02.836Z