Yan, YangTian, and Jinyu Tian. “Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep Models”. Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 9 (April 11, 2025): 9130–9138. Accessed May 13, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/32988.