Lu, Hui, Yi Yu, Song Xia, Yiming Yang, Deepu Rajan, Boon Poh Ng, Alex Kot, and Xudong Jiang. “From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 9 (March 14, 2026): 7548–7556. Accessed May 12, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/37695.