Rong, X., Huang, W., Jiang, W., Li, Y., Wang, W., & Ye, M. (2026). Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language Model. Proceedings of the AAAI Conference on Artificial Intelligence, 40(42), 35775–35783. https://doi.org/10.1609/aaai.v40i42.40891