Kumbam, Pranath Reddy, et al. “Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models”. Proceedings of the International AAAI Conference on Web and Social Media, vol. 19, no. 1, June 2025, pp. 1038-50, doi:10.1609/icwsm.v19i1.35859.