@inproceedings{nizar-kobren-2020-leveraging,
    title = "Leveraging Extracted Model Adversaries for Improved Black Box Attacks",
    author = "Nizar, Naveen Jafer  and
      Kobren, Ari",
    editor = "Alishahi, Afra  and
      Belinkov, Yonatan  and
      Chrupa{\l}a, Grzegorz  and
      Hupkes, Dieuwke  and
      Pinter, Yuval  and
      Sajjad, Hassan",
    booktitle = "Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2020.blackboxnlp-1.6/",
    doi = "10.18653/v1/2020.blackboxnlp-1.6",
    pages = "57--67",
    abstract = "We present a method for adversarial input generation against black box models for reading comprehension based question answering. Our approach is composed of two steps. First, we approximate a victim black box model via model extraction. Second, we use our own white box method to generate input perturbations that cause the approximate model to fail. These perturbed inputs are used against the victim. In experiments we find that our method improves on the efficacy of the ADDANY{---}a white box attack{---}performed on the approximate model by 25{\%} F1, and the ADDSENT attack{---}a black box attack{---}by 11{\%} F1."
}