WU, Yuhang; ARORA, Sunpreet S; WU, Yanhong; YANG, Hao. Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 35, n. 4, p. 2969–2977, 2021. DOI: 10.1609/aaai.v35i4.16404. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/16404. Acesso em: 13 may. 2026.