Rong, X. et al. 2026. Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language Model. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 42 (Mar. 2026), 35775–35783. DOI:https://doi.org/10.1609/aaai.v40i42.40891.