Wang, Longwei, Ifrat Ikhtear Uddin, Xiao Qin, Yang Zhou, and KC Santosh. “Explainability-Driven Defense: Grad-CAM-Guided Model Refinement Against Adversarial Threats”. Proceedings of the AAAI Symposium Series 6, no. 1 (August 1, 2025): 49–57. Accessed May 16, 2026. https://ojs.aaai.org/index.php/AAAI-SS/article/view/36024.