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.
CITATION STYLE
Emmery, C., Kádár, Á., & Chrupała, G. (2021). Adversarial stylometry in the wild: Transferable lexical substitution attacks on author profiling. In EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 2388–2402). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.eacl-main.203
Mendeley helps you to discover research relevant for your work.