@inproceedings{emmery-etal-2021-adversarial,
    title = "Adversarial Stylometry in the Wild: {T}ransferable Lexical Substitution Attacks on Author Profiling",
    author = "Emmery, Chris  and
      K{\'a}d{\'a}r, {\'A}kos  and
      Chrupa{\l}a, Grzegorz",
    editor = "Merlo, Paola  and
      Tiedemann, Jorg  and
      Tsarfaty, Reut",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.eacl-main.203/",
    doi = "10.18653/v1/2021.eacl-main.203",
    pages = "2388--2402",
    abstract = "Written language contains stylistic cues that can be exploited to automatically infer a variety of potentially sensitive author information. Adversarial stylometry intends to attack such models by rewriting an author`s text. Our research proposes several components to facilitate deployment of these adversarial attacks in the wild, where neither data nor target models are accessible. We introduce a transformer-based extension of a lexical replacement attack, and show it achieves high transferability when trained on a weakly labeled corpus{---}decreasing target model performance below chance. While not completely inconspicuous, our more successful attacks also prove notably less detectable by humans. Our framework therefore provides a promising direction for future privacy-preserving adversarial attacks."
}