Xu L. auteur aut IRD Cuesta-Infante A. auteur aut IRD Berti-Equille Laure auteur aut IRD Veeramachaneni K. auteur aut IRD text conferencePaper eng text/pdf born digital access Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically similar to the original sentences and preserve the original labels, while causing the classifier to misclassify them. Existing methods prioritize misclassification by maximizing each perturbation's effectiveness at misleading a text classifier; thus, the generated adversarial examples fall short in terms of fluency and similarity. In this paper, we propose a rewrite and rollback (R&R) framework for adversarial attack. It improves the quality of adversarial examples by optimizing a critique score which combines the fluency, similarity, and misclassification metrics. R&R generates high-quality adversarial examples by allowing exploration of perturbations that do not have immediate impact on the misclassification metric but can improve fluency and similarity metrics. We evaluate our method on 5 representative datasets and 3 classifier architectures. Our method outperforms current state-of-the-art in attack success rate by +16.2%, +12.8%, and +14.0% on the classifiers respectively. specialized 122 The Asia-Pacific Chapter of the Association for Computational Linguistics-International Joint Conference on Natural Language Processing : AACL-IJCNLP 2022, 2. ; 12., [en ligne], 2022/11/20-23 438-452 Zong C. ed. edt IRD Xia F. ed. edt IRD Li W. ed. edt IRD Navigli R. ed. edt IRD [s.l.] Association for Computational Linguistics 2022 https://www.documentation.ird.fr/hor/fdi:010090487 10.48550/arXiv.2104.08453 [F B010090487] https://www.documentation.ird.fr/hor/fdi:010090487 https://www.documentation.ird.fr/intranet/publi/2023-11/010090487.pdf Accès réservé (Intranet de l'IRD) IRD - Base Horizon / Pleins textes 2023-11-03 2025-02-24 fdi:010090487 fre