[1]
Huang, L. et al. 2026. Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 7 (Mar. 2026), 5067–5075. DOI:https://doi.org/10.1609/aaai.v40i7.37420.