Kumbam PR, Syed SU, Thamminedi P, Harish S, Perera I, Dorr BJ. Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models. ICWSM [Internet]. 2025 Jun. 7 [cited 2026 May 29];19(1):1038-50. Available from: https://ojs.aaai.org/index.php/ICWSM/article/view/35859