Zhang, X., Liu, H., Guo, S., Zhang, S., Zhang, T., & Xiang, T. (2026). ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMs. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 34845–34853. https://doi.org/10.1609/aaai.v40i41.40787